Un pipeline GraphRAG entièrement local utilisant LangExtract, Neo4j, Qdrant et Ollama

Cette version est un système GraphRAG qui fonctionne entièrement avec des modèles locaux. Les composants sont Ollama pour les modèles linguistiques et d’incorporation, Neo4j pour le graphe, Qdrant pour la recherche vectorielle et LangExtract pour extraire la structure du texte. Au lieu de récupérer des fragments de documents comme le fait un RAG classique, il transforme le texte brut en un graphe de connaissances, récupère les entités sémantiquement proches d’une question, puis suit les relations qui les relient.

L’élément clé de cette conception est LangExtract, qui identifie les entités et les relations dans du texte non structuré et les restitue sous une forme que le graphe peut stocker. Qdrant apporte du sens grâce à la similarité vectorielle, tandis que Neo4j fournit un contexte par le biais de parcours. Ensemble, ils forment un pipeline de récupération conscient à la fois du sujet d’une question et des liens entre les faits.

Comment fonctionne l’architecture

Le texte brut entre d’abord dans la couche LangExtract. Les pipelines conventionnels découperaient immédiatement les documents en blocs pour les intégrer. Ici, le texte est d’abord transformé en connaissances structurées avant toute autre étape. LangExtract, soutenu par un modèle hébergé sur Ollama, identifie les entités ainsi que les relations qui les lient. L’exemple présenté concerne des données médicamenteuses : les médicaments, leurs doses, leur fréquence d’administration et les affections médicales associées sont extraits, et leurs liens sont conservés grâce à un regroupement commun. Le langage naturel devient ainsi un enregistrement structuré de faits et non simplement un ensemble de passages stockés.

Ensuite, les entités et relations extraites deviennent des parties du graphe. Chaque concept se transforme en un nœud doté d’une ID unique, tandis que des relations telles que la dose, la fréquence ou l’état deviennent des arêtes explicites entre les nœuds. Les informations sont désormais organisées autour des entités et de leurs connexions, et non autour des limites des documents, ce qui permet de conserver le contexte que la récupération basée sur des blocs perdrait normalement.

Le graphe est ensuite chargé dans Neo4j, le principal stockage de connaissances structurées. Les entités deviennent des nœuds et les relations deviennent des arêtes natives. Comme Neo4j peut parcourir efficacement les concepts connectés, le système peut par la suite suivre des chemins à plusieurs étapes et mettre en évidence un contexte situé au-delà du point où l’extraction a commencé.

Lorsque le graphe est construit, une représentation vectorielle est générée pour chaque nœud. Le modèle de représentation vectorielle lit directement les noms d’entités et les concepts, sans avoir à traiter des documents ou des segments entiers. Le résultat est un index sémantique des entités du graphe, ce qui permet une recherche axée sur les concepts plutôt que sur des passages entiers.

Ces vecteurs sont envoyés dans Qdrant accompagnés des IDs des nœuds correspondants de Neo4j. Qdrant agit comme couche sémantique rapide, tandis que Neo4j reste la base de données structurée. Étant donné que chaque envoi vers Qdrant contient un ID de nœud Neo4j, une correspondance vectorielle se traduit directement par une entité du graphe. Cette séparation permet à chaque base de données d’exécuter ce pour quoi elle est la plus adaptée : la recherche de similarité dans l’une, et le parcours des relations ainsi que le raisonnement sur le graphe dans l’autre.

Lors de la requête, un utilisateur pose une question en langue naturelle. Le même modèle d’embedding la transforme en un vecteur, qui est recherché dans Qdrant afin de trouver les entités graphiques les plus pertinentes. Au lieu de fragments de documents, la recherche renvoie des identifiants de nœuds. Ces nœuds servent de points d’entrée sémantiques dans le graphe, représentant les concepts les plus proches de ce que souhaite l’utilisateur.

Ces identifiants permettent ensuite de lancer une requête vers Neo4j. Au lieu de s’arrêter aux entités correspondantes, le système se développe vers les nœuds et relations voisins et collecte un sous-graphe pertinent contenant à la fois les correspondances et leur contexte environnant. Cette expansion permet de rassembler des faits complémentaires que la similarité vectorielle seule ne pourrait pas déceler, de sorte que le contexte apporte à la fois pertinence sémantique et structure.

Le sous-graphe est ensuite reformé pour un modèle de langage. Les nœuds sont regroupés en une liste structurée, et les relations deviennent des triples lisible indiquant des connexions explicites, telles que « dose de Lisinopril : 10 mg » ou « utilisation du Metformin pour le diabète ». Cette étape relie les bases de données graphiques aux modèles de langage en transformant la structure du graphe en texte que le modèle peut interpréter.

Finalement, le contexte graphique formaté est transmis au LLM. Le modèle reçoit des entités et des relations, et non des extraits récupérés, ce qui lui permet de raisonner sur les faits indiqués sans avoir à déduire des liens à partir de passages fragmentés. Comme le contexte provient d’une exploration du graphe, il est également plus expliquable et traçable que la récupération vectorielle ordinaire.

En somme, il s’agit d’un système de recherche hybride. LangExtract s’occupe de l’extraction des connaissances, Neo4j gère les relations structurées, Qdrant récupère les entités de manière sémantique, et le LLM raisonne à partir d’un contexte ancré dans un graphe. En combinant la similarité avec le parcours des liens, ce système répond aux questions à partir de connaissances interconnectées et non à partir de fragments de texte isolés. Cela rend cette approche particulièrement efficace dans des domaines tels que la santé, la finance, le droit, la gestion des connaissances d’entreprise et la recherche scientifique, où les relations entre entités ont souvent plus d’importance que n’importe quel passage isolé.

Méthode par méthode

__init__() est le point d’entrée de tout le système. Il lit les paramètres de configuration à partir des variables d’environnement, y compris les identifiants Neo4j, les détails de connexion à Qdrant ainsi que les paramètres d’Ollama. Il établit des connexions vers Neo4j et Qdrant que le reste du pipeline réutilise, et il crée le client Ollama utilisé pour l’extraction, la génération d’embeddings et la synthèse des réponses. Les noms des modèles et les dimensions vectorielles sont stockés en tant que paramètres, ce qui permet de garder la configuration adaptable.

def __init__(self,env_path: str = ".env",ollama_model_extract: str = "gemma3:latest",
            ollama_model_answer: str = "gemma3:latest",ollama_embedding_model: str = "embeddinggemma:latest",
            ollama_host: str | None = None,vector_dimension: int = 768,
    ):

        load_dotenv(env_path)

        self.qdrant_key = os.getenv("QDRANT_KEY")
        self.qdrant_url = os.getenv("QDRANT_URL")
        self.neo4j_uri = os.getenv("NEO4J_URI")
        self.neo4j_username = os.getenv("NEO4J_USERNAME")
        self.neo4j_password = os.getenv("NEO4J_PASSWORD")

        self.neo4j_driver = GraphDatabase.driver(
            self.neo4j_uri, auth=(self.neo4j_username, self.neo4j_password)
        )

        self.qdrant_client = QdrantClient(
            url=self.qdrant_url,
            api_key=self.qdrant_key,
        )

        # Ollama client for local embeddings (embeddinggemma:latest)
        self.ollama_client = ollama.Client(host=ollama_host) if ollama_host else ollama.Client()

        # langextract needs a plain URL string, not a client object
        self.ollama_url = ollama_host or os.environ.get("OLLAMA_HOST", "http://localhost:11434")

        # Model / config knobs
        self.ollama_model_extract = ollama_model_extract
        self.ollama_model_answer = ollama_model_answer
        self.ollama_embedding_model = ollama_embedding_model
        self.vector_dimension = vector_dimension

extract_graph_components() transforme du texte brut en connaissances structurées. Il fournit des instructions d’extraction ainsi que des exemples qui guident LangExtract vers les entités et relations appropriées. Un modèle hébergé sur Ollama traite ensuite l’entrée et extrait les médicaments, les doses, les fréquences d’utilisation ainsi que les affections concernées. Ce qui est retourné reste un ensemble d’éléments extraits et non un graphe, c’est pourquoi la méthode les transmet pour la construction du graphe.

def extract_graph_components(self, raw_data: str):
        """Extract medication entities and relationships using langextract + Ollama."""

        prompt_description = textwrap.dedent("""
            Extract medications with their details, using attributes to group related information:
            1. Extract entities in the order they appear in the text
            2. Each entity must have a 'medication_group' attribute linking it to its medication
            3. All details about a medication should share the same medication_group value
            """).strip()

        examples = [
            lx.data.ExampleData(
                text=(
                    "Patient takes Aspirin 100mg daily for heart health and"
                    " Simvastatin 20mg at bedtime."
                ),
                extractions=[
                    lx.data.Extraction(
                        extraction_class="medication",
                        extraction_text="Aspirin",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="dosage",
                        extraction_text="100mg",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="frequency",
                        extraction_text="daily",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="condition",
                        extraction_text="heart health",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="medication",
                        extraction_text="Simvastatin",
                        attributes={"medication_group": "Simvastatin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="dosage",
                        extraction_text="20mg",
                        attributes={"medication_group": "Simvastatin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="frequency",
                        extraction_text="at bedtime",
                        attributes={"medication_group": "Simvastatin"},
                    ),
                ],
            )
        ]

        result = lx.extract(
            text_or_documents=raw_data,
            prompt_description=prompt_description,
            examples=examples,
            model_id=self.ollama_model_extract,
            model_url=self.ollama_url,
            resolver_params={"format_handler": lx_ollama.OLLAMA_FORMAT_HANDLER},
            max_char_buffer=4000,
            show_progress=True,
        )

        return self._convert_extractions_to_graph(result.extractions)

_convert_extractions_to_graph() restructure les extraits sous forme de graphe. Il regroupe les éléments liés entre eux et choisit l’entité principale de chaque groupe comme nœud d’ancre. Chaque nœud reçoit un identifiant unique afin que Neo4j et Qdrant restent cohérents. Les arêtes relient ensuite les nœuds d’ancre à leurs attributs, préservant ainsi le sens initial. Le résultat est un ensemble de nœuds et d’arêtes prêt à être utilisé dans une base de données graphique.

def _convert_extractions_to_graph(self, extractions: list):
        """Convert langextract's flat, grouped extractions into (nodes, relationships)."""

        groups: dict[str, list] = {}
        for ext in extractions:
            if not ext.attributes or "medication_group" not in ext.attributes:
                continue
            group_name = ext.attributes["medication_group"]
            groups.setdefault(group_name, []).append(ext)

        nodes: dict[str, str] = {}
        relationships: list[dict] = []

        for group_name, group_extractions in groups.items():
            anchor_ext = next(
                (e for e in group_extractions if e.extraction_class == "medication"),
                None,
            )

            # Fall back to the group name itself if no explicit "medication"
            # extraction was found in this group, so we still get an anchor.
            anchor_text = anchor_ext.extraction_text if anchor_ext else group_name

            if anchor_text not in nodes:
                nodes[anchor_text] = str(uuid.uuid4())

            for ext in group_extractions:
                if ext is anchor_ext:
                    continue

                target_text = ext.extraction_text
                if target_text not in nodes:
                    nodes[target_text] = str(uuid.uuid4())

                relationships.append(
                    {
                        "source": nodes[anchor_text],
                        "target": nodes[target_text],
                        "type": ext.extraction_class,
                    }
                )

        return nodes, relationships

ingest_to_neo4j() écrit le graphe dans Neo4j, où chaque entité est stockée en tant que nœud et chaque relation en tant qu’arête. Cette structure permet une navigation et une exploration efficaces par la suite. Chaque nœud conserve son identifiant unique, ce qui lui permet de se relier aux résultats de recherche vectorielle. Lorsque la méthode est terminée, le graphe constitue le stock de connaissances structuré du système.

def ingest_to_neo4j(self, nodes: dict, relationships: list):
        """
        Ingest nodes and relationships into Neo4j.
        """
        with self.neo4j_driver.session() as session:
            # Create nodes in Neo4j
            for name, node_id in nodes.items():
                session.run(
                    "CREATE (n:Entity {id: $id, name: $name})",
                    id=node_id,
                    name=name,
                )

            # Create relationships in Neo4j, using the semantic type
            # (dosage/frequency/condition/etc.) as the actual relationship
            # label instead of a generic "RELATIONSHIP" type.
            for relationship in relationships:
                rel_type = self._sanitize_relationship_type(relationship["type"])
                session.run(
                    "MATCH (a:Entity {id: $source_id}), (b:Entity {id: $target_id}) "
                    f"CREATE (a)-[:{rel_type} {{type: $type}}]->(b)",
                    source_id=relationship["source"],
                    target_id=relationship["target"],
                    type=relationship["type"],
                )

        return nodes

_sanitize_relationship_type() existe parce que les noms de relations proviennent des sorties des modèles de langage grand public et peuvent contenir des caractères invalides ou des formats inhabituels. Il nettoie et normalise ces étiquettes avant qu’elles n’arrivent chez Neo4j, générant des identifiants en majuscules sûrs qui respectent les règles de Cypher. Il protège également contre des noms mal formatés et les problèmes de requête qu’ils pourraient provoquer. Cette méthode est simple, mais elle contribue à maintenir la cohérence du graphe.

@staticmethod
    def _sanitize_relationship_type(raw_type: str) -> str:
        """
        Cypher relationship types can't be passed as query parameters, so
        they have to be interpolated into the query string directly. Since
        raw_type comes from LLM-extracted text, sanitize it to a safe
        UPPER_SNAKE_CASE identifier before interpolation, to avoid Cypher
        injection or syntax errors from unexpected characters.
        """
        safe = "".join(ch if ch.isalnum() else "_" for ch in raw_type.strip())
        safe = safe.upper().strip("_") or "RELATIONSHIP"
        if safe[0].isdigit():
            safe = f"REL_{safe}"
        return safe

create_collection() s’assure qu’une collection Qdrant existe avant que des vecteurs ne soient stockés. Il vérifie si la collection désignée est déjà présente et la crée le cas échéant, en configurant la dimension des vecteurs ainsi que la métrique de similarité utilisée pour les recherches. Cette vérification préalable permet d’éviter de recréer inutilement des collections et met la couche vectorielle prête avant le début de l’ingestion.

def create_collection(self, collection_name: str, vector_dimension: int = None):
        vector_dimension = vector_dimension or self.vector_dimension

        try:
            # Try to fetch the collection status
            self.qdrant_client.get_collection(collection_name)
            print(f"Skipping creating collection; '{collection_name}' already exists.")
        except Exception as e:
            # If collection does not exist, an error will be thrown, so we create the collection
            if "Not found: Collection" in str(e) or "doesn't exist" in str(e) or "404" in str(e):
                print(f"Collection '{collection_name}' not found. Creating it now...")

                self.qdrant_client.create_collection(
                    collection_name=collection_name,
                    vectors_config=models.VectorParams(
                        size=vector_dimension, distance=models.Distance.COSINE
                    ),
                )

                print(f"Collection '{collection_name}' created successfully.")
            else:
                print(f"Error while checking collection: {e}")

ollama_embeddings() génère des vecteurs densifs à l’aide du modèle d’encodage d’Ollama. Chaque entité de graphe et chaque requête utilisateur y passe. Ces vecteurs expriment le sens de manière numérique, ce qui permet de les comparer efficacement, et c’est ce qui permet la recherche de similarité dans Qdrant. En fait, cette méthode constitue le pont entre le langage naturel et la récupération vectorielle.

def ollama_embeddings(self, text: str) -> list[float]:
        response = self.ollama_client.embeddings(
            model=self.ollama_embedding_model,
            prompt=text,
        )
        return response["embedding"]

ingest_to_qdrant() crée une représentation vectorielle pour chaque entité dès que les nœuds du graphe existent, et la stocke dans Qdrant. Aux côtés de chaque vecteur, il conserve des métadonnées, à savoir l’identifiant du nœud Neo4j et le nom de l’entité. Ce lien relie la base de données vectorielle à la base de données graphique, permettant ainsi de traduire ultérieurement les résultats de recherche en entités graphiques. Cette méthode constitue la couche de recherche sémantique de l’architecture.

def ingest_to_qdrant(self, collection_name: str, raw_data: str, node_id_mapping: dict):
        names = list(node_id_mapping.keys())
        embeddings = [self.ollama_embeddings(name) for name in names]

        self.qdrant_client.upsert(
            collection_name=collection_name,
            points=[
                {
                    "id": str(uuid.uuid4()),
                    "vector": embedding,
                    "payload": {"id": node_id_mapping[name], "name": name},
                }
                for name, embedding in zip(names, embeddings)
            ],
        )

retriever_search() effectue une recherche sémantique au moment de la requête. La requête est intégrée et comparée aux vecteurs présents dans Qdrant. Ce qui est retourné, ce sont des entités graphiques similaires à la requête et non des fragments de texte, ces dernières servant de points d’entrée dans le graphique de connaissances. La recherche est donc guidée par des concepts et non par des documents.

def retriever_search(self, collection_name: str, query: str, top_k: int = 5):
        retriever = QdrantNeo4jRetriever(
            driver=self.neo4j_driver,
            client=self.qdrant_client,
            collection_name=collection_name,
            id_property_external="id",
            id_property_neo4j="id",
        )

        results = retriever.search(
            query_vector=self.ollama_embeddings(query), top_k=top_k
        )

        return results

fetch_related_graph() demande à Neo4j les éléments environnants des entités venant d’être trouvées. Il parcourt le graphe afin de collecter les nœuds voisins ainsi que les relations qui les relient aux entités récupérées. Cette expansion ajoute un contexte que la correspondance vectorielle aurait pu manquer et produit un sous-graphe significatif plutôt que des entités isolées. Cette étape permet à GraphRAG de raisonner sur les relations.

def fetch_related_graph(self, entity_ids: list):
        query = """
        MATCH (e:Entity)-[r1]-(n1)-[r2]-(n2)
        WHERE e.id IN $entity_ids
        RETURN e, r1 as r, n1 as related, r2, n2
        UNION
        MATCH (e:Entity)-[r]-(related)
        WHERE e.id IN $entity_ids
        RETURN e, r, related, null as r2, null as n2
        """
        with self.neo4j_driver.session() as session:
            result = session.run(query, entity_ids=entity_ids)
            subgraph = []
            for record in result:
                subgraph.append(
                    {
                        "entity": record["e"],
                        "relationship": record["r"],
                        "related_node": record["related"],
                    }
                )
                if record["r2"] and record["n2"]:
                    subgraph.append(
                        {
                            "entity": record["related"],
                            "relationship": record["r2"],
                            "related_node": record["n2"],
                        }
                    )
        return subgraph

format_graph_context() prépare le sous-graphe pour le modèle, car la sortie brute du graphe n’est pas directement adaptée à un LLM. Il convertit la structure en texte lisible composé de nœuds et d’énoncés de relations, présentés sous forme de triples faciles à comprendre qui décrivent comment les entités sont connectées. Ce format conserve la structure du graphe tout en restant simple à interpréter par un modèle de langage. C’est la dernière étape de préparation du contexte avant de répondre.

def format_graph_context(self, subgraph: list):
        nodes = set()
        edges = []

        for entry in subgraph:
            entity = entry["entity"]
            related = entry["related_node"]
            relationship = entry["relationship"]

            nodes.add(entity["name"])
            nodes.add(related["name"])

            edges.append(f"{entity['name']} {relationship['type']} {related['name']}")

        return {"nodes": list(nodes), "edges": edges}

graphRAG_run() produit la réponse finale. Il combine le contexte du graphe formaté avec la question de l’utilisateur pour former une requête. Le modèle reçoit des informations ancrées dans le graphe et non des extraits bruts de documents, ce qui lui permet de raisonner sur les relations et les faits connectés, et sa réponse s’appuie sur les connaissances du graphe récupérées. Il s’agit de la couche de raisonnement à la fin du processus.

def graphRAG_run(self, graph_context: dict, user_query: str):
        nodes_str = ", ".join(graph_context["nodes"])
        edges_str = "; ".join(graph_context["edges"])
        prompt = f"""
        You are an intelligent assistant with access to the following knowledge graph:

        Nodes: {nodes_str}

        Edges: {edges_str}

        Using this graph, Answer the following question:

        User Query: "{user_query}"
        """

        try:
            response = chat(
                model=self.ollama_model_answer,
                messages=[
                    {
                        "role": "system",
                        "content": "Provide the answer for the following question:",
                    },
                    {"role": "user", "content": prompt},
                ],
            )
            return response.message.content

        except Exception as e:
            return f"Error querying LLM: {str(e)}"

create_and_ingest() coordonne l’ensemble du flux de travail d’ingestion : création de la collection vectorielle, extraction des composants du graphe, stockage de ceux-ci dans Neo4j, génération d’embeddings et indexation des entités dans Qdrant. Son exécution transforme du texte brut en une base de connaissances GraphRAG consultable. Elle s’exécute généralement une seule fois, lors de la préparation des données, après quoi le système peut répondre aux requêtes.

def create_and_ingest(self, raw_data: str, query: str, collection_name: str = "medicationGraphRAGstore"):
        print("Creating collection...")
        self.create_collection(collection_name, self.vector_dimension)
        print("Collection created/verified")

        print("Extracting graph components...")
        nodes, relationships = self.extract_graph_components(raw_data)
        print("Nodes:", nodes)
        print("Relationships:", relationships)

        print("Ingesting to Neo4j...")
        node_id_mapping = self.ingest_to_neo4j(nodes, relationships)
        print("Neo4j ingestion complete")

        print("Ingesting to Qdrant...")
        self.ingest_to_qdrant(collection_name, raw_data, node_id_mapping)
        print("Qdrant ingestion complete")

run_pipeline() coordonne la récupération des informations et le raisonnement du début à la fin. Il commence par une récupération sémantique dans Qdrant, résout les entités du graphe correspondantes, puis parcourt Neo4j. Le sous-graphe résultant est formaté pour être utilisé par le modèle de raisonnement, et la réponse générée est renvoyée à l’utilisateur. Il représente le parcours complet de la question à la réponse.

def run_pipeline(self, raw_data: str, query: str, collection_name: str = "medicationGraphRAGstore"):

        # run only the first time, comment this for subsequent runs
        # self.create_and_ingest(raw_data, query, collection_name)

        print("Starting retriever search...")
        retriever_result = self.retriever_search(collection_name, query)
        print("Retriever results:", retriever_result)

        print("Extracting entity IDs...")
        entity_ids = [
            item.content.split("'id': '")[1].split("'")[0]
            for item in retriever_result.items
        ]
        print("Entity IDs:", entity_ids)

        print("Fetching related graph...")
        subgraph = self.fetch_related_graph(entity_ids)
        print("Subgraph:", subgraph)

        print("Formatting graph context...")
        graph_context = self.format_graph_context(subgraph)
        print("Graph context:", graph_context)

        print("Running GraphRAG...")
        answer = self.graphRAG_run(graph_context, query)
        print("Final Answer:", answer)

        return answer

close() s’occupe du nettoyage. Il ferme la connexion au pilote Neo4j et libère les ressources associées, ce qui empêche les fuites de connexion et permet une fermeture propre. C’est simple, mais il doit toujours être appelé à la fin du traitement.

def close(self):
        self.neo4j_driver.close()

Le code du pilote relie les éléments de la classe entre eux :

if __name__ == "__main__":
    print("Script started")

    graph_rag = MedicationGraphRAG(env_path="../.env")

    # Example-1
    # raw_data = textwrap.dedent("""
    #     The patient was prescribed Lisinopril and Metformin last month.
    #     He takes the Lisinopril 10mg daily for hypertension, but often misses
    #     his Metformin 500mg dose which should be taken twice daily for diabetes.
    #     """).strip()

    # Example-2
    raw_data = textwrap.dedent("""
    The patient is a 62-year-old man with a history of multiple chronic conditions
    being managed through an extensive medication regimen. He was prescribed
    Lisinopril, Metformin, Atorvastatin, Aspirin, Levothyroxine, and Sertraline
    over the course of the past year, with his treatment plan adjusted several
    times based on follow-up visits.

    He takes Lisinopril 10mg daily for hypertension, but often misses his
    Metformin 500mg dose which should be taken twice daily for diabetes. His
    cardiologist also started him on Atorvastatin 40mg at bedtime for high
    cholesterol after his last lipid panel showed elevated LDL levels. To reduce
    his risk of cardiovascular events, he was additionally prescribed Aspirin
    81mg daily for heart disease prevention, which he takes alongside his
    breakfast each morning.

    Following a routine thyroid screening, he was found to have an underactive
    thyroid and was started on Levothyroxine 75mcg every morning for
    hypothyroidism, to be taken on an empty stomach before any other medications.
    More recently, after reporting persistent low mood and difficulty sleeping
    during a wellness visit, his primary care physician added Sertraline 50mg
    daily for depression, with plans to reassess the dosage after eight weeks.

    Despite the number of prescriptions, the patient has had difficulty
    maintaining consistency with his Metformin and occasionally forgets his
    evening Atorvastatin dose, which his care team is now addressing through a
    simplified pill organizer and reminder system.
    """).strip()

    # Sample Questions
    #1. "What is the dosage and frequency for Lisinopril?"
    #2. "What is the dosage and frequency for Metformin?"
    #3. "Which medications does the patient take once daily versus twice daily?"
    #4. "What medication is prescribed for hypothyroidism, and at what dose?"
    #5. "List all medications related to cardiovascular conditions and their dosages."
    #6. "How often does the patient take Aspirin?"
    #7. "What condition is Levothyroxine prescribed for?"
    #8. "What time of day should Levothyroxine be taken, and why?"
    #9. "Which medications does the patient have trouble taking consistently?"
    #10. "What is the dosage and frequency for Sertraline?"

    query = "List all medications related to cardiovascular conditions and their dosages."

    answer = graph_rag.run_pipeline(raw_data, query, collection_name="medicationGraphRAGstore")

    graph_rag.close()

Le script complet

Tous les éléments réunis dans un seul fichier :

import os
import uuid
import textwrap

import ollama
from dotenv import load_dotenv, find_dotenv
from ollama import chat
from neo4j import GraphDatabase
from qdrant_client import QdrantClient, models
from neo4j_graphrag.retrievers import QdrantNeo4jRetriever

import langextract as lx
from langextract.providers import ollama as lx_ollama

load_dotenv(find_dotenv())


class MedicationGraphRAG:

    def __init__(self,env_path: str = ".env",ollama_model_extract: str = "gemma3:latest",
            ollama_model_answer: str = "gemma3:latest",ollama_embedding_model: str = "embeddinggemma:latest",
            ollama_host: str | None = None,vector_dimension: int = 768,
    ):

        load_dotenv(env_path)

        self.qdrant_key = os.getenv("QDRANT_KEY")
        self.qdrant_url = os.getenv("QDRANT_URL")
        self.neo4j_uri = os.getenv("NEO4J_URI")
        self.neo4j_username = os.getenv("NEO4J_USERNAME")
        self.neo4j_password = os.getenv("NEO4J_PASSWORD")

        self.neo4j_driver = GraphDatabase.driver(
            self.neo4j_uri, auth=(self.neo4j_username, self.neo4j_password)
        )

        self.qdrant_client = QdrantClient(
            url=self.qdrant_url,
            api_key=self.qdrant_key,
        )

        # Ollama client for local embeddings (embeddinggemma:latest)
        self.ollama_client = ollama.Client(host=ollama_host) if ollama_host else ollama.Client()

        # langextract needs a plain URL string, not a client object
        self.ollama_url = ollama_host or os.environ.get("OLLAMA_HOST", "http://localhost:11434")

        # Model / config knobs
        self.ollama_model_extract = ollama_model_extract
        self.ollama_model_answer = ollama_model_answer
        self.ollama_embedding_model = ollama_embedding_model
        self.vector_dimension = vector_dimension

    def extract_graph_components(self, raw_data: str):
        """Extract medication entities and relationships using langextract + Ollama."""

        prompt_description = textwrap.dedent("""
            Extract medications with their details, using attributes to group related information:
            1. Extract entities in the order they appear in the text
            2. Each entity must have a 'medication_group' attribute linking it to its medication
            3. All details about a medication should share the same medication_group value
            """).strip()

        examples = [
            lx.data.ExampleData(
                text=(
                    "Patient takes Aspirin 100mg daily for heart health and"
                    " Simvastatin 20mg at bedtime."
                ),
                extractions=[
                    lx.data.Extraction(
                        extraction_class="medication",
                        extraction_text="Aspirin",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="dosage",
                        extraction_text="100mg",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="frequency",
                        extraction_text="daily",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="condition",
                        extraction_text="heart health",
                        attributes={"medication_group": "Aspirin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="medication",
                        extraction_text="Simvastatin",
                        attributes={"medication_group": "Simvastatin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="dosage",
                        extraction_text="20mg",
                        attributes={"medication_group": "Simvastatin"},
                    ),
                    lx.data.Extraction(
                        extraction_class="frequency",
                        extraction_text="at bedtime",
                        attributes={"medication_group": "Simvastatin"},
                    ),
                ],
            )
        ]

        result = lx.extract(
            text_or_documents=raw_data,
            prompt_description=prompt_description,
            examples=examples,
            model_id=self.ollama_model_extract,
            model_url=self.ollama_url,
            resolver_params={"format_handler": lx_ollama.OLLAMA_FORMAT_HANDLER},
            max_char_buffer=4000,
            show_progress=True,
        )

        return self._convert_extractions_to_graph(result.extractions)

    def _convert_extractions_to_graph(self, extractions: list):
        """Convert langextract's flat, grouped extractions into (nodes, relationships)."""

        groups: dict[str, list] = {}
        for ext in extractions:
            if not ext.attributes or "medication_group" not in ext.attributes:
                continue
            group_name = ext.attributes["medication_group"]
            groups.setdefault(group_name, []).append(ext)

        nodes: dict[str, str] = {}
        relationships: list[dict] = []

        for group_name, group_extractions in groups.items():
            anchor_ext = next(
                (e for e in group_extractions if e.extraction_class == "medication"),
                None,
            )

            # Fall back to the group name itself if no explicit "medication"
            # extraction was found in this group, so we still get an anchor.
            anchor_text = anchor_ext.extraction_text if anchor_ext else group_name

            if anchor_text not in nodes:
                nodes[anchor_text] = str(uuid.uuid4())

            for ext in group_extractions:
                if ext is anchor_ext:
                    continue

                target_text = ext.extraction_text
                if target_text not in nodes:
                    nodes[target_text] = str(uuid.uuid4())

                relationships.append(
                    {
                        "source": nodes[anchor_text],
                        "target": nodes[target_text],
                        "type": ext.extraction_class,
                    }
                )

        return nodes, relationships

    def ingest_to_neo4j(self, nodes: dict, relationships: list):
        """
        Ingest nodes and relationships into Neo4j.
        """
        with self.neo4j_driver.session() as session:
            # Create nodes in Neo4j
            for name, node_id in nodes.items():
                session.run(
                    "CREATE (n:Entity {id: $id, name: $name})",
                    id=node_id,
                    name=name,
                )

            # Create relationships in Neo4j, using the semantic type
            # (dosage/frequency/condition/etc.) as the actual relationship
            # label instead of a generic "RELATIONSHIP" type.
            for relationship in relationships:
                rel_type = self._sanitize_relationship_type(relationship["type"])
                session.run(
                    "MATCH (a:Entity {id: $source_id}), (b:Entity {id: $target_id}) "
                    f"CREATE (a)-[:{rel_type} {{type: $type}}]->(b)",
                    source_id=relationship["source"],
                    target_id=relationship["target"],
                    type=relationship["type"],
                )

        return nodes

    @staticmethod
    def _sanitize_relationship_type(raw_type: str) -> str:
        """
        Cypher relationship types can't be passed as query parameters, so
        they have to be interpolated into the query string directly. Since
        raw_type comes from LLM-extracted text, sanitize it to a safe
        UPPER_SNAKE_CASE identifier before interpolation, to avoid Cypher
        injection or syntax errors from unexpected characters.
        """
        safe = "".join(ch if ch.isalnum() else "_" for ch in raw_type.strip())
        safe = safe.upper().strip("_") or "RELATIONSHIP"
        if safe[0].isdigit():
            safe = f"REL_{safe}"
        return safe

    def create_collection(self, collection_name: str, vector_dimension: int = None):
        vector_dimension = vector_dimension or self.vector_dimension

        try:
            # Try to fetch the collection status
            self.qdrant_client.get_collection(collection_name)
            print(f"Skipping creating collection; '{collection_name}' already exists.")
        except Exception as e:
            # If collection does not exist, an error will be thrown, so we create the collection
            if "Not found: Collection" in str(e) or "doesn't exist" in str(e) or "404" in str(e):
                print(f"Collection '{collection_name}' not found. Creating it now...")

                self.qdrant_client.create_collection(
                    collection_name=collection_name,
                    vectors_config=models.VectorParams(
                        size=vector_dimension, distance=models.Distance.COSINE
                    ),
                )

                print(f"Collection '{collection_name}' created successfully.")
            else:
                print(f"Error while checking collection: {e}")

    def ollama_embeddings(self, text: str) -> list[float]:
        response = self.ollama_client.embeddings(
            model=self.ollama_embedding_model,
            prompt=text,
        )
        return response["embedding"]

    def ingest_to_qdrant(self, collection_name: str, raw_data: str, node_id_mapping: dict):
        names = list(node_id_mapping.keys())
        embeddings = [self.ollama_embeddings(name) for name in names]

        self.qdrant_client.upsert(
            collection_name=collection_name,
            points=[
                {
                    "id": str(uuid.uuid4()),
                    "vector": embedding,
                    "payload": {"id": node_id_mapping[name], "name": name},
                }
                for name, embedding in zip(names, embeddings)
            ],
        )

    def retriever_search(self, collection_name: str, query: str, top_k: int = 5):
        retriever = QdrantNeo4jRetriever(
            driver=self.neo4j_driver,
            client=self.qdrant_client,
            collection_name=collection_name,
            id_property_external="id",
            id_property_neo4j="id",
        )

        results = retriever.search(
            query_vector=self.ollama_embeddings(query), top_k=top_k
        )

        return results

    def fetch_related_graph(self, entity_ids: list):
        query = """
        MATCH (e:Entity)-[r1]-(n1)-[r2]-(n2)
        WHERE e.id IN $entity_ids
        RETURN e, r1 as r, n1 as related, r2, n2
        UNION
        MATCH (e:Entity)-[r]-(related)
        WHERE e.id IN $entity_ids
        RETURN e, r, related, null as r2, null as n2
        """
        with self.neo4j_driver.session() as session:
            result = session.run(query, entity_ids=entity_ids)
            subgraph = []
            for record in result:
                subgraph.append(
                    {
                        "entity": record["e"],
                        "relationship": record["r"],
                        "related_node": record["related"],
                    }
                )
                if record["r2"] and record["n2"]:
                    subgraph.append(
                        {
                            "entity": record["related"],
                            "relationship": record["r2"],
                            "related_node": record["n2"],
                        }
                    )
        return subgraph

    def format_graph_context(self, subgraph: list):
        nodes = set()
        edges = []

        for entry in subgraph:
            entity = entry["entity"]
            related = entry["related_node"]
            relationship = entry["relationship"]

            nodes.add(entity["name"])
            nodes.add(related["name"])

            edges.append(f"{entity['name']} {relationship['type']} {related['name']}")

        return {"nodes": list(nodes), "edges": edges}

    def graphRAG_run(self, graph_context: dict, user_query: str):
        nodes_str = ", ".join(graph_context["nodes"])
        edges_str = "; ".join(graph_context["edges"])
        prompt = f"""
        You are an intelligent assistant with access to the following knowledge graph:

        Nodes: {nodes_str}

        Edges: {edges_str}

        Using this graph, Answer the following question:

        User Query: "{user_query}"
        """

        try:
            response = chat(
                model=self.ollama_model_answer,
                messages=[
                    {
                        "role": "system",
                        "content": "Provide the answer for the following question:",
                    },
                    {"role": "user", "content": prompt},
                ],
            )
            return response.message.content

        except Exception as e:
            return f"Error querying LLM: {str(e)}"

    def create_and_ingest(self, raw_data: str, query: str, collection_name: str = "medicationGraphRAGstore"):
        print("Creating collection...")
        self.create_collection(collection_name, self.vector_dimension)
        print("Collection created/verified")

        print("Extracting graph components...")
        nodes, relationships = self.extract_graph_components(raw_data)
        print("Nodes:", nodes)
        print("Relationships:", relationships)

        print("Ingesting to Neo4j...")
        node_id_mapping = self.ingest_to_neo4j(nodes, relationships)
        print("Neo4j ingestion complete")

        print("Ingesting to Qdrant...")
        self.ingest_to_qdrant(collection_name, raw_data, node_id_mapping)
        print("Qdrant ingestion complete")

    def run_pipeline(self, raw_data: str, query: str, collection_name: str = "medicationGraphRAGstore"):

        # run only the first time, comment this for subsequent runs
        # self.create_and_ingest(raw_data, query, collection_name)

        print("Starting retriever search...")
        retriever_result = self.retriever_search(collection_name, query)
        print("Retriever results:", retriever_result)

        print("Extracting entity IDs...")
        entity_ids = [
            item.content.split("'id': '")[1].split("'")[0]
            for item in retriever_result.items
        ]
        print("Entity IDs:", entity_ids)

        print("Fetching related graph...")
        subgraph = self.fetch_related_graph(entity_ids)
        print("Subgraph:", subgraph)

        print("Formatting graph context...")
        graph_context = self.format_graph_context(subgraph)
        print("Graph context:", graph_context)

        print("Running GraphRAG...")
        answer = self.graphRAG_run(graph_context, query)
        print("Final Answer:", answer)

        return answer

    def close(self):
        self.neo4j_driver.close()

if __name__ == "__main__":
    print("Script started")

    graph_rag = MedicationGraphRAG(env_path="../.env")

    # Example-1
    # raw_data = textwrap.dedent("""
    #     The patient was prescribed Lisinopril and Metformin last month.
    #     He takes the Lisinopril 10mg daily for hypertension, but often misses
    #     his Metformin 500mg dose which should be taken twice daily for diabetes.
    #     """).strip()

    # Example-2
    raw_data = textwrap.dedent("""
    The patient is a 62-year-old man with a history of multiple chronic conditions
    being managed through an extensive medication regimen. He was prescribed
    Lisinopril, Metformin, Atorvastatin, Aspirin, Levothyroxine, and Sertraline
    over the course of the past year, with his treatment plan adjusted several
    times based on follow-up visits.

    He takes Lisinopril 10mg daily for hypertension, but often misses his
    Metformin 500mg dose which should be taken twice daily for diabetes. His
    cardiologist also started him on Atorvastatin 40mg at bedtime for high
    cholesterol after his last lipid panel showed elevated LDL levels. To reduce
    his risk of cardiovascular events, he was additionally prescribed Aspirin
    81mg daily for heart disease prevention, which he takes alongside his
    breakfast each morning.

    Following a routine thyroid screening, he was found to have an underactive
    thyroid and was started on Levothyroxine 75mcg every morning for
    hypothyroidism, to be taken on an empty stomach before any other medications.
    More recently, after reporting persistent low mood and difficulty sleeping
    during a wellness visit, his primary care physician added Sertraline 50mg
    daily for depression, with plans to reassess the dosage after eight weeks.

    Despite the number of prescriptions, the patient has had difficulty
    maintaining consistency with his Metformin and occasionally forgets his
    evening Atorvastatin dose, which his care team is now addressing through a
    simplified pill organizer and reminder system.
    """).strip()

    # Sample Questions
    #1. "What is the dosage and frequency for Lisinopril?"
    #2. "What is the dosage and frequency for Metformin?"
    #3. "Which medications does the patient take once daily versus twice daily?"
    #4. "What medication is prescribed for hypothyroidism, and at what dose?"
    #5. "List all medications related to cardiovascular conditions and their dosages."
    #6. "How often does the patient take Aspirin?"
    #7. "What condition is Levothyroxine prescribed for?"
    #8. "What time of day should Levothyroxine be taken, and why?"
    #9. "Which medications does the patient have trouble taking consistently?"
    #10. "What is the dosage and frequency for Sertraline?"

    query = "List all medications related to cardiovascular conditions and their dosages."

    answer = graph_rag.run_pipeline(raw_data, query, collection_name="medicationGraphRAGstore")

    graph_rag.close()

Le fonctionnement

Trois questions d’exemple montrent le système en action. Chacune affiche d’abord les résultats obtenus par le moteur de recherche, puis la réponse basée sur le graphique.

query = "List all medications related to cardiovascular conditions and their dosages."

Console:
Starting retriever search...
Retriever results: items=[RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}> score=0.5062605>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:0' labels=frozenset({'Entity'}) properties={'name': 'Atorvastatin', 'id': '1db81626-c3de-4cab-b5dd-091327785182'}> score=0.47961158>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}> score=0.45777896>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}> score=0.45199984>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}> score=0.4511963>", metadata=None)] metadata={'__retriever': 'QdrantNeo4jRetriever'}
Extracting entity IDs...
Entity IDs: ['1c9fb28e-c3e1-4515-afa0-01939beac419', '1db81626-c3de-4cab-b5dd-091327785182', '44573186-869f-4d5d-ba04-fe254ec4ed21', '04f27c55-38a3-46a9-a411-4faf07836a56', '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb']
Fetching related graph...
Subgraph: [{'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:5' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:4' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:5' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:3' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:5' labels=frozenset({'Entity'}) properties={'name': '81mg', 'id': '9d1d3859-cf6f-4a22-81b8-7d80e3cc8e89'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:5' labels=frozenset({'Entity'}) properties={'name': '81mg', 'id': '9d1d3859-cf6f-4a22-81b8-7d80e3cc8e89'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:7' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:17' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:7' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:4' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:13' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:12' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:0' labels=frozenset({'Entity'}) properties={'name': 'Atorvastatin', 'id': '1db81626-c3de-4cab-b5dd-091327785182'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:2' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:0' labels=frozenset({'Entity'}) properties={'name': 'Atorvastatin', 'id': '1db81626-c3de-4cab-b5dd-091327785182'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:3' labels=frozenset({'Entity'}) properties={'name': 'high cholesterol', 'id': 'dc85b413-3eca-4f26-a1dd-95de9d61e46c'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:3' labels=frozenset({'Entity'}) properties={'name': 'high cholesterol', 'id': 'dc85b413-3eca-4f26-a1dd-95de9d61e46c'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:0' labels=frozenset({'Entity'}) properties={'name': 'Atorvastatin', 'id': '1db81626-c3de-4cab-b5dd-091327785182'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:1' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:0' labels=frozenset({'Entity'}) properties={'name': 'Atorvastatin', 'id': '1db81626-c3de-4cab-b5dd-091327785182'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:2' labels=frozenset({'Entity'}) properties={'name': 'at bedtime', 'id': 'f9a049d4-bdb9-443d-a70f-3aa0ad290f5d'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:2' labels=frozenset({'Entity'}) properties={'name': 'at bedtime', 'id': 'f9a049d4-bdb9-443d-a70f-3aa0ad290f5d'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:0' labels=frozenset({'Entity'}) properties={'name': 'Atorvastatin', 'id': '1db81626-c3de-4cab-b5dd-091327785182'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:0' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:0' labels=frozenset({'Entity'}) properties={'name': 'Atorvastatin', 'id': '1db81626-c3de-4cab-b5dd-091327785182'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:1' labels=frozenset({'Entity'}) properties={'name': '40mg', 'id': '960fd15d-ad36-4b90-aede-3473dd53f70c'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:1' labels=frozenset({'Entity'}) properties={'name': '40mg', 'id': '960fd15d-ad36-4b90-aede-3473dd53f70c'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:5' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:13' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:12' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:8' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:11' labels=frozenset({'Entity'}) properties={'name': 'hypertension', 'id': '1bc0479e-5e00-4ede-8a9d-704e56f58814'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:11' labels=frozenset({'Entity'}) properties={'name': 'hypertension', 'id': '1bc0479e-5e00-4ede-8a9d-704e56f58814'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:7' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:6' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}]
Formatting graph context...
Graph context: {'nodes': ['on an empty stomach before any other medications', 'hypertension', 'Atorvastatin', 'Lisinopril', 'Levothyroxine', 'at bedtime', 'high cholesterol', 'Aspirin', '75mcg', '81mg', 'daily', '10mg', 'heart disease prevention', 'every morning', 'Sertraline', 'hypothyroidism', '40mg'], 'edges': ['heart disease prevention condition Aspirin', 'Aspirin frequency daily', 'heart disease prevention condition Aspirin', 'Aspirin dosage 81mg', 'Lisinopril frequency daily', 'daily frequency Sertraline', 'Lisinopril frequency daily', 'daily frequency Aspirin', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine condition hypothyroidism', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine frequency every morning', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine dosage 75mcg', 'Atorvastatin condition high cholesterol', 'Atorvastatin frequency at bedtime', 'Atorvastatin dosage 40mg', 'heart disease prevention condition Aspirin', 'Levothyroxine route on an empty stomach before any other medications', 'Levothyroxine condition hypothyroidism', 'Levothyroxine frequency every morning', 'Levothyroxine dosage 75mcg', 'Lisinopril condition hypertension', 'Lisinopril frequency daily', 'Lisinopril dosage 10mg', 'on an empty stomach before any other medications route Levothyroxine']}
Running GraphRAG...
Final Answer: Here’s a list of medications related to cardiovascular conditions and their dosages based on the knowledge graph:

*   **Aspirin:** 81mg (frequency: daily) - for heart disease prevention.
*   **Atorvastatin:** 40mg (frequency: at bedtime) - for high cholesterol.
*   **Lisinopril:** 10mg (frequency: daily) - for hypertension.

query = "What medication is prescribed for hypothyroidism, and at what dose?"

Console:
Starting retriever search...
Retriever results: items=[RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}> score=0.6616618>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}> score=0.5983002>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}> score=0.4675771>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}> score=0.4620626>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}> score=0.4382253>", metadata=None)] metadata={'__retriever': 'QdrantNeo4jRetriever'}
Extracting entity IDs...
Entity IDs: ['95b91440-5ff1-41eb-a036-b57880094b05', '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb', 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847', '1c9fb28e-c3e1-4515-afa0-01939beac419', 'cddff401-0958-4093-b196-ad270b7aa797']
Fetching related graph...
Subgraph: [{'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:6' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:8' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:11' labels=frozenset({'Entity'}) properties={'name': 'hypertension', 'id': '1bc0479e-5e00-4ede-8a9d-704e56f58814'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:11' labels=frozenset({'Entity'}) properties={'name': 'hypertension', 'id': '1bc0479e-5e00-4ede-8a9d-704e56f58814'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:6' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:7' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:13' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:12' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:13' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:12' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:13' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:12' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:6' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:11' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:10' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:9' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}]
Formatting graph context...
Graph context: {'nodes': ['Lisinopril', '75mcg', 'twice daily', 'diabetes', 'on an empty stomach before any other medications', 'hypertension', 'daily', 'Metformin', '500mg', '10mg', 'hypothyroidism', 'Levothyroxine', 'every morning'], 'edges': ['10mg dosage Lisinopril', 'Lisinopril condition hypertension', '10mg dosage Lisinopril', 'Lisinopril frequency daily', 'hypothyroidism condition Levothyroxine', 'Levothyroxine route on an empty stomach before any other medications', 'hypothyroidism condition Levothyroxine', 'Levothyroxine frequency every morning', 'hypothyroidism condition Levothyroxine', 'Levothyroxine dosage 75mcg', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine condition hypothyroidism', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine frequency every morning', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine dosage 75mcg', 'Levothyroxine route on an empty stomach before any other medications', 'Levothyroxine condition hypothyroidism', 'Levothyroxine frequency every morning', 'Levothyroxine dosage 75mcg', '10mg dosage Lisinopril', 'Metformin condition diabetes', 'Metformin frequency twice daily', 'Metformin dosage 500mg', 'hypothyroidism condition Levothyroxine', 'on an empty stomach before any other medications route Levothyroxine']}
Running GraphRAG...
Final Answer: Levothyroxine 75mcg is prescribed for hypothyroidism, taken every morning.

query = "Which medications does the patient take once daily versus twice daily?"

Console:
Starting retriever search...
Retriever results: items=[RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}> score=0.6052238>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}> score=0.50138044>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}> score=0.424541>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}> score=0.42364278>", metadata=None), RetrieverResultItem(content="<Record node=<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}> score=0.4210245>", metadata=None)] metadata={'__retriever': 'QdrantNeo4jRetriever'}
Extracting entity IDs...
Entity IDs: ['73d5a502-05be-4bb7-916a-10b8ff5130fa', '1c9fb28e-c3e1-4515-afa0-01939beac419', '06da6faa-baa5-4657-a961-5091f58e3058', '9cbb512f-ca6b-47de-bb12-378ac35826bd', 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847']
Fetching related graph...
Subgraph: [{'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:17' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:18' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:22' labels=frozenset({'Entity'}) properties={'name': 'depression', 'id': '3aca7091-a4fa-4b12-ba5a-a8dbbbac5df4'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:22' labels=frozenset({'Entity'}) properties={'name': 'depression', 'id': '3aca7091-a4fa-4b12-ba5a-a8dbbbac5df4'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:17' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:16' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:21' labels=frozenset({'Entity'}) properties={'name': '50mg', 'id': '5fe00dee-bd0f-4476-b5a6-b19974033f78'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:21' labels=frozenset({'Entity'}) properties={'name': '50mg', 'id': '5fe00dee-bd0f-4476-b5a6-b19974033f78'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:4' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:5' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:6' labels=frozenset({'Entity'}) properties={'name': 'heart disease prevention', 'id': '44573186-869f-4d5d-ba04-fe254ec4ed21'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:4' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:3' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:5' labels=frozenset({'Entity'}) properties={'name': '81mg', 'id': '9d1d3859-cf6f-4a22-81b8-7d80e3cc8e89'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:5' labels=frozenset({'Entity'}) properties={'name': '81mg', 'id': '9d1d3859-cf6f-4a22-81b8-7d80e3cc8e89'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:7' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:8' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:11' labels=frozenset({'Entity'}) properties={'name': 'hypertension', 'id': '1bc0479e-5e00-4ede-8a9d-704e56f58814'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:11' labels=frozenset({'Entity'}) properties={'name': 'hypertension', 'id': '1bc0479e-5e00-4ede-8a9d-704e56f58814'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:7' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:6' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:9' labels=frozenset({'Entity'}) properties={'name': '10mg', 'id': 'cddff401-0958-4093-b196-ad270b7aa797'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:10' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:11' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:10' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:9' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:11' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:10' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:11' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:9' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:14' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:18' labels=frozenset({'Entity'}) properties={'name': 'hypothyroidism', 'id': '95b91440-5ff1-41eb-a036-b57880094b05'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:13' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:17' labels=frozenset({'Entity'}) properties={'name': 'every morning', 'id': '7fb1c7e5-e414-43ec-8606-474b08dc9173'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:12' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:16' labels=frozenset({'Entity'}) properties={'name': '75mcg', 'id': '75b6f7a1-2f53-419c-9365-5f026dcb1e25'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:17' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:20' labels=frozenset({'Entity'}) properties={'name': 'Sertraline', 'id': '42844c4c-ce96-4bd9-8d37-d8adad5a75fe'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:4' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:4' labels=frozenset({'Entity'}) properties={'name': 'Aspirin', 'id': '10939c85-6fc1-41b4-9b80-abe1662eda11'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:7' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:10' labels=frozenset({'Entity'}) properties={'name': 'daily', 'id': '06da6faa-baa5-4657-a961-5091f58e3058'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:8' labels=frozenset({'Entity'}) properties={'name': 'Lisinopril', 'id': '04f27c55-38a3-46a9-a411-4faf07836a56'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:11' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:10' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:9' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>) type='DOSAGE' properties={'type': 'dosage'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:13' labels=frozenset({'Entity'}) properties={'name': '500mg', 'id': '6c38fe32-0ca3-4bcc-a072-05e302aaa8e7'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:10' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:14' labels=frozenset({'Entity'}) properties={'name': 'twice daily', 'id': '73d5a502-05be-4bb7-916a-10b8ff5130fa'}>) type='FREQUENCY' properties={'type': 'frequency'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:11' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:15' labels=frozenset({'Entity'}) properties={'name': 'diabetes', 'id': '9cbb512f-ca6b-47de-bb12-378ac35826bd'}>) type='CONDITION' properties={'type': 'condition'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:12' labels=frozenset({'Entity'}) properties={'name': 'Metformin', 'id': 'd14d70ef-3780-4ebe-b803-1ab8bd8ec847'}>}, {'entity': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>, 'relationship': <Relationship element_id='5:a53f7783-1308-4f3d-9a27-45cede6b6376:15' nodes=(<Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>, <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:19' labels=frozenset({'Entity'}) properties={'name': 'on an empty stomach before any other medications', 'id': '1c9fb28e-c3e1-4515-afa0-01939beac419'}>) type='ROUTE' properties={'type': 'route'}>, 'related_node': <Node element_id='4:a53f7783-1308-4f3d-9a27-45cede6b6376:7' labels=frozenset({'Entity'}) properties={'name': 'Levothyroxine', 'id': '60654f2d-2ec8-4f4e-be02-cd57b7c5abfb'}>}]
Formatting graph context...
Graph context: {'nodes': ['twice daily', 'daily', '75mcg', '50mg', '81mg', 'Aspirin', 'on an empty stomach before any other medications', 'hypothyroidism', 'hypertension', 'depression', 'Lisinopril', 'Levothyroxine', 'heart disease prevention', 'every morning', 'Sertraline', 'diabetes', '500mg', '10mg', 'Metformin'], 'edges': ['daily frequency Sertraline', 'Sertraline condition depression', 'daily frequency Sertraline', 'Sertraline dosage 50mg', 'daily frequency Aspirin', 'Aspirin condition heart disease prevention', 'daily frequency Aspirin', 'Aspirin dosage 81mg', 'daily frequency Lisinopril', 'Lisinopril condition hypertension', 'daily frequency Lisinopril', 'Lisinopril dosage 10mg', 'twice daily frequency Metformin', 'Metformin condition diabetes', 'twice daily frequency Metformin', 'Metformin dosage 500mg', 'diabetes condition Metformin', 'Metformin frequency twice daily', 'diabetes condition Metformin', 'Metformin dosage 500mg', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine condition hypothyroidism', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine frequency every morning', 'on an empty stomach before any other medications route Levothyroxine', 'Levothyroxine dosage 75mcg', 'daily frequency Sertraline', 'daily frequency Aspirin', 'daily frequency Lisinopril', 'Metformin condition diabetes', 'Metformin frequency twice daily', 'Metformin dosage 500mg', 'twice daily frequency Metformin', 'diabetes condition Metformin', 'on an empty stomach before any other medications route Levothyroxine']}
Running GraphRAG...
Final Answer: Here’s the breakdown of medications taken once daily versus twice daily based on the knowledge graph:

**Once Daily:**

*   Aspirin: daily frequency
*   Sertraline: daily frequency
*   Levothyroxine: every morning frequency

**Twice Daily:**

*   Metformin: twice daily frequency

Ce que montre la compilation

Le résultat est un pipeline GraphRAG complet, dont chaque composant fonctionne localement sur Ollama, Neo4j, Qdrant et LangExtract. Le texte non structuré devient une connaissance structurée grâce à l’extraction d’entités et de relations, et cette connaissance est stockée sous forme de graphe dans Neo4j. Qdrant permet une recherche sémantique sur les entités du graphe et relie la recherche vectorielle à la navigation dans le graphe. Ensemble, ils remplacent la recherche basée sur des fragments de texte par une recherche consciente du contexte, pilotée par des connaissances interconnectées, permettant ainsi à un LLM de raisonner sur des relations plutôt que sur des fragments de texte isolés, ce qui produit des réponses mieux fondées et plus faciles à expliquer. Comme toute l’infrastructure est locale, les développeurs conservent un contrôle total sur leurs données, leurs modèles et leur infrastructure. À mesure que l’adoption de GraphRAG augmente, un tel design offre un modèle pratique pour une recherche consciente des relations, construite à l’aide d’outils open source.