RAG agentiel avec Agno Teams : réécriture des requêtes, boucle de critique et Qdrant
RAG agentiel avec une équipe Agno : un coordinateur réécrit les requêtes, un critique itère la récupération des données, et les réponses proviennent uniquement du contexte approuvé dans la recherche hybride Qdrant.
Sources: The Agent Coordinator Pattern: Orchestrating Query Rewriting, Retrieval, and Critique with Agno
Un cycle de récupération critique entre des agents est facile à esquisser sur un tableau blanc, mais étonnamment difficile à mettre en fonctionnement. Le système décrit ici fonctionne sur Agno Teams et comporte quatre rôles : un coordinateur, un réécrivain de requêtes, un cycle chargé d’affiner constamment le contexte, et un agent de réponse qui ne donne de réponse qu’une fois que les preuves sont suffisantes. En sous-sol se trouve une récupération hybride dans Qdrant, combinant des vecteurs denses, BM25 et une fusion de classements réciproques.
Organisation de l’équipe
En tête se trouve le coordinateur, un Team en mode coordinate. Il ne réalise aucune tâche par lui-même. Il distribue les tâches, attend, puis transmet chaque résultat le long de la chaîne.
- L’agent de réécriture des requêtes prend la question brute et génère de trois à cinq variantes sémantiquement similaires. Des formulations différentes font apparaître des passages différents, et une seule formulation trouve rarement tout ce qui est pertinent.
- Le cycle de récupération et de critique est là où le véritable travail a lieu. Une deuxième
Team, mise en modetaskset limitée parmax_iterations, est placée à l’intérieur du coordinateur en tant que membre unique. À l’intérieur, un agent de récupération effectue une recherche hybride pour chaque variante auprès de Qdrant, en mélangeant des vecteurs denses et spars avec un réclassement en phase tardive. Un agent de critique évalue ensuite les résultats obtenus en termes de pertinence et de couverture. Une couverture insuffisante fait relancer la requête sous une forme affinée, tandis qu’une bonne couverture permet d’obtenir l’approbation. Le cycle se termine lorsque le critique est satisfait ou lorsque le budget d’itérations est épuisé, selon ce qui se produit en premier. - L’agent de réponse ne voit que le contexte approuvé, jamais les résultats bruts de la récupération. Il répond strictement à partir de ce matériel, indique quel passage étaye quelle affirmation, et précise clairement lorsque le contexte est insuffisant.
- La réponse finale remonte via le coordinateur sans être modifiée, sans réécriture ni réexamen.
Pourquoi placer une équipe à l’intérieur d’une autre équipe ? Cela transpose l’idée de critique et de boucle sur le mécanisme d’itération propre à Agno, de sorte qu’il n’y a pas de boucle while manuellement écrite dans le code de l’application. Le coordinateur ne voit qu’un seul élément propre, et toute logique de tentative est conservée à l’intérieur de cet élément.
Construction de la base de connaissances
Aucun agent ne peut récupérer quoi que ce soit tant que la base de connaissances n’existe pas, et bien la concevoir est tout aussi important que la conception de l’agent.
Le jeu de données correspondant est MedQuAD_Context_GroupedQA, comprenant environ 8 000 passages médicaux chacun accompagné de paires de questions-réponses regroupées. L’importation ne conserve que la colonne context. Les paires QA restent telles quelles dans le jeu de données, car l’expérience vise à tester la récupération à partir de passages bruts plutôt que la mémorisation des réponses.
Il n’y a pas de segmentation en blocs. Le contexte complet de chaque ligne est intégré et stocké sous forme d’un seul point Qdrant. Cela simplifie la compréhension, au prix de la dépendance aux mécanismes de troncature propres aux API d’incorporation pour les contextes longs.
Chaque point contient trois vecteurs, chacun dans son propre emplacement nommé, ce qui permet d’obtenir une collection offrant trois vues complémentaires du même texte :
dense: une incorporation Gemini à 768 dimensionssparse: de BM25 à FastEmbedlate_interaction: un multivector ColBERT utilisé pour le réclassement, et non pour la recherche en première passe
Enfin, il y a le contrat de charge utile. L’intégration Qdrant d’Agno attend des clés de charge utile spécifiques (name, content, meta_data et content_id) afin de pouvoir reconstruire ses objets Document internes au moment de la recherche.
Code du projet
Les fichiers se trouvent dans un petit arbre :
.
├── data_ingester.py
├── in-context-learning-agentic-team.py
├── pyproject.toml
├── .env
└── uv.lock
La configuration globale vient en premier, couvrant les importations, le modèle et l’objet de connaissance :
import os
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIChat
from agno.knowledge.embedder.google import GeminiEmbedder
from agno.team import Team
from agno.team.mode import TeamMode
from agno.vectordb.qdrant import Qdrant
from agno.vectordb.search import SearchType
from dotenv import load_dotenv, find_dotenv
# ---------------------------------------------------------------------------
# Shared config
# ---------------------------------------------------------------------------
load_dotenv(find_dotenv())
MODEL_ID = "gpt-4o"
COLLECTION_NAME = os.getenv("QDRANT_COLLECTION", "medquad_hybrid")
# Must match the ingestion script's model/dimensions exactly, or the query
# vector lands in the wrong embedding space entirely.
embedder = GeminiEmbedder(
id=os.getenv("GEMINI_EMBEDDING_MODEL", "gemini-embedding-2-preview"),
dimensions=768,
api_key=os.getenv("GEMINI_API_KEY"),
)
vector_db = Qdrant(
collection=COLLECTION_NAME,
url=os.getenv("QDRANT_URL", "http://localhost:6333"),
api_key=os.getenv("QDRANT_API_KEY"),
embedder=embedder,
search_type=SearchType.hybrid,
)
knowledge_base = Knowledge(
vector_db=vector_db,
)
Réécrivain de requête
Cet agent ne dispose d’aucun outil, seulement des capacités linguistiques. Face à une question, il génère de trois à cinq variantes qui diffèrent par leur formulation, leur niveau de spécificité et leurs synonymes. L’objectif est de jeter un filet légèrement plus large avant de commencer la recherche.
# ---------------------------------------------------------------------------
# 1. Query Rewriting Agent
# ---------------------------------------------------------------------------
query_rewriter = Agent(
name="Query Rewriting Agent",
role="Given a user query, generate N semantically similar reformulations",
model=OpenAIChat(id=MODEL_ID),
instructions=[
"Given the user's query, produce 3 to 5 semantically similar variants.",
"Vary phrasing, specificity, and synonyms so each variant could surface "
"different but relevant passages during retrieval.",
"Return the variants as a clean numbered list, nothing else.",
],
add_datetime_to_context=True,
)
Agent de récupération
Parmi tous les agents, c’est celui qui interroge directement Qdrant. Chaque variante de requête fait l’objet d’une recherche fusionnée dense-plus-spars, et les résultats retournés sont annotés indiquant leur source ainsi que leur score ; un réordonneur d’interaction tardive est disponible si nécessaire. Ses instructions stipulent de signaler « rien trouvé » et de ne jamais inventer de passage semblant crédible.
# ---------------------------------------------------------------------------
# 2. Retrieval Agent (Qdrant-backed knowledge)
# ---------------------------------------------------------------------------
retrieval_agent = Agent(
name="Retrieval Agent",
role="Search the Qdrant knowledge base for passages relevant to a query",
model=OpenAIChat(id=MODEL_ID),
knowledge=knowledge_base,
search_knowledge=True,
instructions=[
"For each incoming query variant, search the knowledge base.",
"Return the retrieved passages verbatim along with their source and "
"similarity score so the Critique Agent can evaluate them.",
"If nothing relevant is found for a variant, say so explicitly instead "
"of fabricating context.",
],
add_datetime_to_context=True,
)
Évaluation de l’agent
Le sceptique du groupe ne répond pas lui-même. Il évalue la pertinence et la complétude des résultats trouvés par l’agent de récupération, puis soit approuve le contexte, soit le renvoie accompagné d’une raison. C’est ce qui transforme une simple récupération en espérant un bon résultat en un véritable cycle de retours d’information.
# ---------------------------------------------------------------------------
# 3. Critique Agent
# ---------------------------------------------------------------------------
critique_agent = Agent(
name="Critique Agent",
role="Critique and self-evaluate retrieved context for relevance and coverage",
model=OpenAIChat(id=MODEL_ID),
instructions=[
"Evaluate the retrieved passages against the original user query.",
"Score relevance and coverage on a 1-5 scale and explain briefly.",
"If coverage is weak (score below 4) or passages are off-topic, "
"explicitly request the Retrieval Agent to retry with a refined query, "
"narrower or broader scope, or different query variant.",
"If coverage is adequate, clearly state that the context is approved "
"and ready to be handed to the Response Generation Agent.",
],
add_datetime_to_context=True,
)
# ---------------------------------------------------------------------------
# Retrieval <-> Critique loop, as a nested tasks-mode sub-team
# ---------------------------------------------------------------------------
retrieval_critique_loop = Team(
name="Retrieval-Critique Loop",
role=(
"Iteratively retrieve context for each query variant and critique it "
"until the context is approved or the iteration budget is exhausted"
),
mode=TeamMode.tasks,
model=OpenAIChat(id=MODEL_ID),
members=[retrieval_agent, critique_agent],
max_iterations=4,
instructions=[
"Run retrieval for every query variant received.",
"After each retrieval pass, send the results to the Critique Agent.",
"If the Critique Agent requests a retry, refine the query and retrieve "
"again.",
"Stop as soon as the Critique Agent approves the context, or when the "
"iteration budget is reached -- whichever comes first.",
"Return the final approved (or best-effort) fused context.",
],
)
Agent de réponse
Seul cet agent communique avec l’utilisateur. Il lit le contexte déjà approuvé par le critique, fonde chaque affirmation sur celui-ci à l’aide de citations, et recourt à un message explicite indiquant un « contexte insuffisant » plutôt que de deviner.
# ---------------------------------------------------------------------------
# 4. Response Generation Agent
# ---------------------------------------------------------------------------
response_agent = Agent(
name="Response Generation Agent",
role="Generate the final answer from the fused, approved context",
model=OpenAIChat(id=MODEL_ID),
instructions=[
"You will receive the original user query and the final fused context "
"approved by the Retrieval-Critique Loop.",
"Answer strictly grounded in the provided context.",
"If the context is insufficient, say so rather than guessing.",
"Cite which passage(s) support each claim where possible.",
],
add_datetime_to_context=True,
)
Coordonnateur
Appeler cela un agent est un exagération, car il s’agit plutôt d’un chef d’orchestre. Il connaît la séquence (rédiger, récupérer et critiquer, répondre) et transmet les résultats sans les modifier. Toute réflexion a lieu ultérieurement, et le coordinateur se contente de s’assurer que les bonnes actions sont effectuées dans le bon ordre.
# ---------------------------------------------------------------------------
# Top-level coordinator
# ---------------------------------------------------------------------------
agent_coordinator = Team(
name="Agent Coordinator",
mode=TeamMode.coordinate,
model=OpenAIChat(id=MODEL_ID),
members=[query_rewriter, retrieval_critique_loop, response_agent],
instructions=[
"You coordinate an agentic RAG pipeline.",
"Step 1: send the user's query to the Query Rewriting Agent to obtain "
"N semantically similar query variants.",
"Step 2: send all query variants to the Retrieval-Critique Loop and "
"wait for the final fused, approved context.",
"Step 3: send the original user query plus the fused context to the "
"Response Generation Agent.",
"Step 4: return the Response Generation Agent's output as the final "
"answer -- do not rewrite or second-guess it.",
],
add_datetime_to_context=True,
show_members_responses=True,
)
Le lancement
Le script d’ingestion relie l’ensemble de données, les trois embedders et Qdrant :
import os
import time
import uuid
from datasets import load_dataset
from fastembed import LateInteractionTextEmbedding, SparseTextEmbedding
from google import genai
from google.genai.types import EmbedContentConfig, HttpOptions, HttpRetryOptions
from qdrant_client import QdrantClient
from qdrant_client.models import (
Distance,
HnswConfigDiff,
Modifier,
MultiVectorComparator,
MultiVectorConfig,
PointStruct,
SparseVector,
SparseVectorParams,
VectorParams,
)
from dotenv import load_dotenv, find_dotenv
# ---------------------------------------------------------------------------
# Config
# ---------------------------------------------------------------------------
load_dotenv(find_dotenv())
DATASET_ID = "pavanmantha/MedQuAD_Context_GroupedQA"
COLLECTION_NAME = os.getenv("QDRANT_COLLECTION", "medquad_hybrid")
# Dense: Google Gemini embedding.
# gemini-embedding-2-preview is Google's newest (multimodal-capable) model;
# swap to "gemini-embedding-001" if you want the GA, text-only model instead.
GEMINI_MODEL = os.getenv("GEMINI_EMBEDDING_MODEL", "gemini-embedding-2-preview")
DENSE_DIM = int(os.getenv("GEMINI_EMBEDDING_DIM", "768")) # Google's recommended sweet spot
# Sparse: BM25 (must be paired with Modifier.IDF on the Qdrant side)
SPARSE_MODEL_NAME = "Qdrant/bm25"
# Late interaction: ColBERT-style multivector, used later for reranking
LATE_INTERACTION_MODEL_NAME = "answerdotai/answerai-colbert-small-v1"
LATE_INTERACTION_DIM = 96 # matches answerai-colbert-small-v1
BATCH_SIZE = 16 # points per upsert batch
# Retry/backoff for Gemini calls (you were hitting 4xx rate limits and
# 5xx "not available" errors -- both are transient and worth retrying)
GEMINI_MAX_ATTEMPTS = int(os.getenv("GEMINI_MAX_ATTEMPTS", "6"))
GEMINI_RETRY_INITIAL_DELAY = float(os.getenv("GEMINI_RETRY_INITIAL_DELAY", "2.0"))
GEMINI_RETRY_MAX_DELAY = float(os.getenv("GEMINI_RETRY_MAX_DELAY", "64.0"))
GEMINI_RETRYABLE_STATUS_CODES = [408, 429, 500, 502, 503, 504]
GEMINI_REQUEST_DELAY_SECONDS = float(os.getenv("GEMINI_REQUEST_DELAY_SECONDS", "0.5"))
# ---------------------------------------------------------------------------
# Clients / models (initialized once)
# ---------------------------------------------------------------------------
genai_client = genai.Client(
http_options=HttpOptions(
retry_options=HttpRetryOptions(
attempts=GEMINI_MAX_ATTEMPTS,
initial_delay=GEMINI_RETRY_INITIAL_DELAY,
max_delay=GEMINI_RETRY_MAX_DELAY,
http_status_codes=GEMINI_RETRYABLE_STATUS_CODES,
)
)
) # picks up GEMINI_API_KEY from env; auto-retries 429/5xx with backoff
qdrant_client = QdrantClient(
url=os.getenv("QDRANT_URL", "http://localhost:6333"),
api_key=os.getenv("QDRANT_API_KEY"),
)
sparse_model = SparseTextEmbedding(model_name=SPARSE_MODEL_NAME)
late_interaction_model = LateInteractionTextEmbedding(model_name=LATE_INTERACTION_MODEL_NAME)
# ---------------------------------------------------------------------------
# Embedding helpers
# ---------------------------------------------------------------------------
def embed_dense(texts: list[str]) -> list[list[float]]:
vectors = []
for text in texts:
result = genai_client.models.embed_content(
model=GEMINI_MODEL,
contents=text,
config=EmbedContentConfig(
task_type="RETRIEVAL_DOCUMENT",
output_dimensionality=DENSE_DIM,
),
)
vectors.append(result.embeddings[0].values)
time.sleep(GEMINI_REQUEST_DELAY_SECONDS) # spacing between calls, tune to your rate limit
return vectors
def embed_sparse(texts: list[str]) -> list[SparseVector]:
"""Sparse BM25 embeddings via FastEmbed -> Qdrant SparseVector."""
sparse_embeddings = list(sparse_model.embed(texts))
return [
SparseVector(indices=se.indices.tolist(), values=se.values.tolist())
for se in sparse_embeddings
]
def embed_late_interaction(texts: list[str]) -> list[list[list[float]]]:
multivectors = list(late_interaction_model.embed(texts))
return [mv.tolist() for mv in multivectors]
# ---------------------------------------------------------------------------
# Collection setup
# ---------------------------------------------------------------------------
def create_collection():
if qdrant_client.collection_exists(collection_name=COLLECTION_NAME):
qdrant_client.delete_collection(collection_name=COLLECTION_NAME)
qdrant_client.create_collection(
collection_name=COLLECTION_NAME,
vectors_config={
"dense": VectorParams(
size=DENSE_DIM,
distance=Distance.COSINE,
),
"late_interaction": VectorParams(
size=LATE_INTERACTION_DIM,
distance=Distance.COSINE,
multivector_config=MultiVectorConfig(
comparator=MultiVectorComparator.MAX_SIM,
),
hnsw_config=HnswConfigDiff(m=0), # reranking-only, no ANN index needed
),
},
sparse_vectors_config={
"sparse": SparseVectorParams(modifier=Modifier.IDF),
},
)
# ---------------------------------------------------------------------------
# Ingestion
# ---------------------------------------------------------------------------
def build_points(chunk_texts: list[str], payloads: list[dict]) -> list[PointStruct]:
dense_vecs = embed_dense(chunk_texts)
sparse_vecs = embed_sparse(chunk_texts)
late_vecs = embed_late_interaction(chunk_texts)
points = []
for text, payload, dense_vec, sparse_vec, late_vec in zip(
chunk_texts, payloads, dense_vecs, sparse_vecs, late_vecs
):
row_idx = payload["source_row_id"]
points.append(
PointStruct(
id=str(uuid.uuid4()),
vector={
"dense": dense_vec,
"sparse": sparse_vec,
"late_interaction": late_vec,
},
payload={
# Required by Agno's Qdrant readback (Document reconstruction):
"name": f"MedQuAD context {row_idx}",
"meta_data": {"source_row_id": row_idx},
"content": text, # the actual context
"usage": None,
"content_id": str(row_idx),
},
)
)
return points
def ingest():
create_collection()
dataset = load_dataset(DATASET_ID, split="train")
batch_texts: list[str] = []
batch_payloads: list[dict] = []
total_ingested = 0
for row_idx, row in enumerate(dataset):
context = row["context"]
batch_texts.append(context)
batch_payloads.append({"source_row_id": row_idx})
if len(batch_texts) >= BATCH_SIZE:
points = build_points(batch_texts, batch_payloads)
qdrant_client.upsert(collection_name=COLLECTION_NAME, points=points)
total_ingested += len(points)
print(f"Ingested {total_ingested} contexts...")
batch_texts, batch_payloads = [], []
# flush remaining
if batch_texts:
points = build_points(batch_texts, batch_payloads)
qdrant_client.upsert(collection_name=COLLECTION_NAME, points=points)
total_ingested += len(points)
print(f"Done. Total contexts ingested: {total_ingested}")
if __name__ == "__main__":
ingest()
Le script principal assemble les agents et l’équipe :
import os
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIChat
from agno.knowledge.embedder.google import GeminiEmbedder
from agno.team import Team
from agno.team.mode import TeamMode
from agno.vectordb.qdrant import Qdrant
from agno.vectordb.search import SearchType
from dotenv import load_dotenv, find_dotenv
# ---------------------------------------------------------------------------
# Shared config
# ---------------------------------------------------------------------------
load_dotenv(find_dotenv())
MODEL_ID = "gpt-4o"
COLLECTION_NAME = os.getenv("QDRANT_COLLECTION", "medquad_hybrid")
# Must match the ingestion script's model/dimensions exactly, or the query
# vector lands in the wrong embedding space entirely.
embedder = GeminiEmbedder(
id=os.getenv("GEMINI_EMBEDDING_MODEL", "gemini-embedding-2-preview"),
dimensions=768,
api_key=os.getenv("GEMINI_API_KEY"),
)
vector_db = Qdrant(
collection=COLLECTION_NAME,
url=os.getenv("QDRANT_URL", "http://localhost:6333"),
api_key=os.getenv("QDRANT_API_KEY"),
embedder=embedder,
search_type=SearchType.hybrid,
)
knowledge_base = Knowledge(
vector_db=vector_db,
)
# ---------------------------------------------------------------------------
# 1. Query Rewriting Agent
# ---------------------------------------------------------------------------
query_rewriter = Agent(
name="Query Rewriting Agent",
role="Given a user query, generate N semantically similar reformulations",
model=OpenAIChat(id=MODEL_ID),
instructions=[
"Given the user's query, produce 3 to 5 semantically similar variants.",
"Vary phrasing, specificity, and synonyms so each variant could surface "
"different but relevant passages during retrieval.",
"Return the variants as a clean numbered list, nothing else.",
],
add_datetime_to_context=True,
)
# ---------------------------------------------------------------------------
# 2. Retrieval Agent (Qdrant-backed knowledge)
# ---------------------------------------------------------------------------
retrieval_agent = Agent(
name="Retrieval Agent",
role="Search the Qdrant knowledge base for passages relevant to a query",
model=OpenAIChat(id=MODEL_ID),
knowledge=knowledge_base,
search_knowledge=True,
instructions=[
"For each incoming query variant, search the knowledge base.",
"Return the retrieved passages verbatim along with their source and "
"similarity score so the Critique Agent can evaluate them.",
"If nothing relevant is found for a variant, say so explicitly instead "
"of fabricating context.",
],
add_datetime_to_context=True,
)
# ---------------------------------------------------------------------------
# 3. Critique Agent
# ---------------------------------------------------------------------------
critique_agent = Agent(
name="Critique Agent",
role="Critique and self-evaluate retrieved context for relevance and coverage",
model=OpenAIChat(id=MODEL_ID),
instructions=[
"Evaluate the retrieved passages against the original user query.",
"Score relevance and coverage on a 1-5 scale and explain briefly.",
"If coverage is weak (score below 4) or passages are off-topic, "
"explicitly request the Retrieval Agent to retry with a refined query, "
"narrower or broader scope, or different query variant.",
"If coverage is adequate, clearly state that the context is approved "
"and ready to be handed to the Response Generation Agent.",
],
add_datetime_to_context=True,
)
# ---------------------------------------------------------------------------
# Retrieval <-> Critique loop, as a nested tasks-mode sub-team
# ---------------------------------------------------------------------------
retrieval_critique_loop = Team(
name="Retrieval-Critique Loop",
role=(
"Iteratively retrieve context for each query variant and critique it "
"until the context is approved or the iteration budget is exhausted"
),
mode=TeamMode.tasks,
model=OpenAIChat(id=MODEL_ID),
members=[retrieval_agent, critique_agent],
max_iterations=4,
instructions=[
"Run retrieval for every query variant received.",
"After each retrieval pass, send the results to the Critique Agent.",
"If the Critique Agent requests a retry, refine the query and retrieve "
"again.",
"Stop as soon as the Critique Agent approves the context, or when the "
"iteration budget is reached -- whichever comes first.",
"Return the final approved (or best-effort) fused context.",
],
)
# ---------------------------------------------------------------------------
# 4. Response Generation Agent
# ---------------------------------------------------------------------------
response_agent = Agent(
name="Response Generation Agent",
role="Generate the final answer from the fused, approved context",
model=OpenAIChat(id=MODEL_ID),
instructions=[
"You will receive the original user query and the final fused context "
"approved by the Retrieval-Critique Loop.",
"Answer strictly grounded in the provided context.",
"If the context is insufficient, say so rather than guessing.",
"Cite which passage(s) support each claim where possible.",
],
add_datetime_to_context=True,
)
# ---------------------------------------------------------------------------
# Top-level coordinator
# ---------------------------------------------------------------------------
agent_coordinator = Team(
name="Agent Coordinator",
mode=TeamMode.coordinate,
model=OpenAIChat(id=MODEL_ID),
members=[query_rewriter, retrieval_critique_loop, response_agent],
instructions=[
"You coordinate an agentic RAG pipeline.",
"Step 1: send the user's query to the Query Rewriting Agent to obtain "
"N semantically similar query variants.",
"Step 2: send all query variants to the Retrieval-Critique Loop and "
"wait for the final fused, approved context.",
"Step 3: send the original user query plus the fused context to the "
"Response Generation Agent.",
"Step 4: return the Response Generation Agent's output as the final "
"answer -- do not rewrite or second-guess it.",
],
add_datetime_to_context=True,
show_members_responses=True,
)
# ---------------------------------------------------------------------------
# Entry point
# ---------------------------------------------------------------------------
if __name__ == "__main__":
# One-time setup: point the knowledge base at your source documents.
# Example (uncomment and edit):
# knowledge_base.add_content(url="https://example.com/your-document.pdf")
# Q1. "What is (are) Small Intestine Cancer? give document citations as reference.",
# Q2. "Who is at risk for Langerhans Cell Histiocytosis?",
# Q3. "What is (are) Langerhans Cell Histiocytosis?",
agent_coordinator.print_response(
"Who is at risk for Langerhans Cell Histiocytosis?",
stream=True,
)
Une exécution complète génère une trace longue, incluant les recherches de documents ainsi que les panneaux de messages de chaque agent :
INFO Found 10 documents
INFO Found 10 documents
INFO Found 10 documents
┏━ Message ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ What is (are) Small Intestine Cancer? ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ Query Rewriting Agent Response ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ 1. What is the disease known as Small Intestine Cancer? ┃
┃ 2. Can you describe Small Intestine Cancer? ┃
┃ 3. How would you define cancer of the small intestine? ┃
┃ 4. What are the characteristics of Small Intestine Cancer? ┃
┃ 5. Could you explain what Small Intestine Cancer entails? ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ Query Rewriting Agent Response ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ 1. What types of cancers affect the small intestine? ┃
┃ 2. Can you list the different forms of cancer found in the small intestine? ┃
┃ 3. How many kinds of small intestine cancers are there? ┃
┃ 4. What are the various cancers of the small intestine? ┃
┃ 5. Could you explain the different types of small intestine cancers? ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ retrieval-agent Tool Calls ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ • search_knowledge_base(query=What is Small Intestine Cancer?) ┃
┃ ┃
┃ • search_knowledge_base(query=What are Small Intestine Cancers?) ┃
┃ ┃
┃ • search_knowledge_base(query=Small Intestine Cancer definition symptoms ┃
┃ treatment options prognosis) ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ retrieval-agent Response ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ Here are the retrieved passages related to Small Intestine Cancer: ┃
┃ ┃
┃ 1. **Passage from MedQuAD context 0:** ┃
┃ - The small intestine is part of the body’s digestive system, which also ┃
┃ includes the esophagus, stomach, and large intestine. The digestive system ┃
┃ removes and processes nutrients (vitamins, minerals, carbohydrates, fats, ┃
┃ proteins, and water) from foods and helps pass waste material out of the ┃
┃ body. The small intestine is a long tube that connects the stomach to the ┃
┃ large intestine. It folds many times to fit inside the abdomen. EnlargeThe ┃
┃ small intestine connects the stomach and the colon. It includes the ┃
┃ duodenum, jejunum, and ileum. The types of cancer found in the small ┃
┃ intestine are adenocarcinoma, sarcoma, carcinoid tumors, gastrointestinal ┃
┃ stromal tumor, and lymphoma. This summary discusses adenocarcinoma and ┃
┃ leiomyosarcoma (a type of sarcoma). Adenocarcinoma starts in glandular cells ┃
┃ in the lining of the small intestine and is the most common type of small ┃
┃ intestine cancer. Most of these tumors occur in the part of the small ┃
┃ intestine near the stomach. They may grow and block the intestine. ┃
┃ Leiomyosarcoma starts in the smooth muscle cells of the small intestine. ┃
┃ Most of these tumors occur in the part of the small intestine near the large ┃
┃ intestine. For more information on small intestine cancer, see the ┃
┃ following: Anything that increases your risk of getting a disease is called ┃
┃ a risk factor. Having a risk factor does not mean that you will get cancer; ┃
┃ not having risk factors doesn't mean that you will not get cancer. Talk with ┃
┃ your doctor if you think you may be at risk. [Source: PMID: 26389461] ┃
┃ ┃
┃ 2. **Passage from MedQuAD context 121:** ┃
┃ - You had surgery to remove all or part of your small intestine (small ┃
┃ bowel). You may also have had an ileostomy. During and after surgery, you ┃
┃ received intravenous (IV) fluids. You also may have had a tube placed ┃
┃ through your nose and into your stomach. You may have received antibiotics. ┃
┃ You may have these problems after you return home from the hospital: Follow ┃
┃ your health care provider's instructions... [Source: Elmously A, Yeo HL. ┃
┃ Management of small bowel obstruction.] ┃
┃ ┃
┃ 3. **Passage from MedQuAD context 209:** ┃
┃ - Radiation enteritis is damage to the lining of the intestines (bowels) ┃
┃ caused by radiation therapy, which is used for some types of cancer ┃
┃ treatment... When symptoms become long-term (chronic), other problems may ┃
┃ include: The health care provider will do a physical exam and ask about your ┃
┃ medical history. Tests may include... [Source: Kuemmerle JF. Inflammatory ┃
┃ and anatomic diseases of the intestine, peritoneum, mesentery, and omentum.] ┃
┃ ┃
┃ These passages were retrieved for both queries, "What is Small Intestine ┃
┃ Cancer?" and "What are Small Intestine Cancers?" They cover an overview, ┃
┃ treatment, and some related conditions and procedures. ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ critique-agent Response ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ **Relevance Score: 4/5** ┃
┃ ┃
┃ The passages include relevant information about Small Intestine Cancer, ┃
┃ especially the types of cancers that can occur in the small intestine, such ┃
┃ as adenocarcinoma and leiomyosarcoma, which directly addresses the query on ┃
┃ what Small Intestine Cancer is. The passage provides important details about ┃
┃ where these cancers are likely to occur within the small intestine and some ┃
┃ general information about risk factors. ┃
┃ ┃
┃ **Coverage Score: 3/5** ┃
┃ ┃
┃ While the passages offer a brief overview and touch on significant points ┃
┃ like types of cancers and risk factors, they do not thoroughly define Small ┃
┃ Intestine Cancer or discuss characteristics, treatment options, symptoms, ┃
┃ diagnosis, or prognosis, which would provide a more comprehensive ┃
┃ understanding. The second and third passages primarily discuss specific ┃
┃ surgical procedures and conditions related to cancer treatment rather than ┃
┃ providing detailed insights into Small Intestinal Cancer itself. ┃
┃ ┃
┃ **Recommendation:** ┃
┃ ┃
┃ The coverage is insufficient for delivering a complete response to the query ┃
┃ about Small Intestine Cancer. It's advisable to request the Retrieval Agent ┃
┃ conduct a more focused search that includes information on defining Small ┃
┃ Intestine Cancer, its symptoms, treatment options, and prognosis. This will ┃
┃ ensure a more comprehensive answer can be given to the user. ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ retrieval-agent Tool Calls ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ • search_knowledge_base(query=What is Small Intestine Cancer?) ┃
┃ ┃
┃ • search_knowledge_base(query=What are Small Intestine Cancers?) ┃
┃ ┃
┃ • search_knowledge_base(query=Small Intestine Cancer definition symptoms ┃
┃ treatment options prognosis) ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ retrieval-agent Response ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ Here are the retrieved passages related to Small Intestine Cancer, including ┃
┃ its definition, symptoms, treatment options, and prognosis: ┃
┃ ┃
┃ 1. **Passage from MedQuAD context 0:** ┃
┃ - The small intestine is part of the body’s digestive system, which also ┃
┃ includes the esophagus, stomach, and large intestine. The digestive system ┃
┃ removes and processes nutrients (vitamins, minerals, carbohydrates, fats, ┃
┃ proteins, and water) from foods and helps pass waste material out of the ┃
┃ body. The small intestine is a long tube that connects the stomach to the ┃
┃ large intestine. It folds many times to fit inside the abdomen. EnlargeThe ┃
┃ small intestine connects the stomach and the colon. It includes the ┃
┃ duodenum, jejunum, and ileum. The types of cancer found in the small ┃
┃ intestine are adenocarcinoma, sarcoma, carcinoid tumors, gastrointestinal ┃
┃ stromal tumor, and lymphoma. Adenocarcinoma starts in glandular cells in the ┃
┃ lining of the small intestine and is the most common type of small intestine ┃
┃ cancer. Most of these tumors occur in the part of the small intestine near ┃
┃ the stomach. They may grow and block the intestine. Leiomyosarcoma starts in ┃
┃ the smooth muscle cells of the small intestine. Most of these tumors occur ┃
┃ in the part of the small intestine near the large intestine. Risk factors ┃
┃ for small intestine cancer include various factors, but having a risk factor ┃
┃ does not mean definite development of cancer. Tests and procedures to ┃
┃ detect, diagnose, and stage small intestine cancer are usually done at the ┃
┃ same time. The prognosis and treatment options depend on the type of small ┃
┃ intestine cancer and whether the tumor can be removed by surgery. Treatment ┃
┃ depends on whether the cancer is being treated as a primary tumor or is ┃
┃ metastatic cancer. Different types of treatments are available, including ┃
┃ surgery, chemotherapy, radiation therapy, and participation in clinical ┃
┃ trials. Many of today's standard treatments are based on earlier clinical ┃
┃ trials, and patients who participate in clinical trials also help improve ┃
┃ future treatments. [PMID: 26389461] ┃
┃ ┃
┃ This passage is comprehensive in providing definitions, symptoms, risk ┃
┃ factors, staging, treatment options, and prognosis regarding Small Intestine ┃
┃ Cancer. It describes different cancers that may affect the small intestine ┃
┃ and the general treatment approach including surgery, chemotherapy, and ┃
┃ clinical trials, offering a holistic understanding of Small Intestine ┃
┃ Cancer. ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ Response Generation Agent Response ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ Small Intestine Cancer is a type of cancer that occurs in the small ┃
┃ intestine, which is part of the body’s digestive system connecting the ┃
┃ stomach to the large intestine. The small intestine extracts and processes ┃
┃ nutrients from foods and assists in passing waste material out of the body. ┃
┃ It includes sections called the duodenum, jejunum, and ileum. ┃
┃ ┃
┃ The types of cancer that can develop in the small intestine include ┃
┃ adenocarcinoma, sarcoma (such as leiomyosarcoma), carcinoid tumors, ┃
┃ gastrointestinal stromal tumors, and lymphoma. Adenocarcinoma, which starts ┃
┃ in the glandular cells lining the small intestine, is the most common type. ┃
┃ These tumors typically form in the part of the small intestine near the ┃
┃ stomach and may grow to block the intestine. Leiomyosarcoma originates in ┃
┃ the smooth muscle cells of the small intestine. ┃
┃ ┃
┃ Several factors may increase the risk of developing small intestine cancer, ┃
┃ though having a risk factor does not guarantee that cancer will develop. ┃
┃ Detection, diagnosis, and staging of small intestine cancer usually occur ┃
┃ simultaneously through various tests and procedures. ┃
┃ ┃
┃ The prognosis and treatment for small intestine cancer depend on the cancer ┃
┃ type and whether the tumor can be removed surgically. Treatment options ┃
┃ include surgery, chemotherapy, radiation therapy, and participation in ┃
┃ clinical trials. These trials are essential as many of today's standard ┃
┃ treatments are based on earlier clinical trial results. Patients who ┃
┃ participate in clinical trials contribute to the potential improvement of ┃
┃ future cancer treatments. ┃
┃ ┃
┃ This comprehensive understanding of Small Intestine Cancer covers its ┃
┃ definition, types, risk factors, diagnosis methods, and treatment practices, ┃
┃ providing an insightful perspective on managing this disease [Source: PMID: ┃
┃ 26389461]. ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ Team Tool Calls ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ • delegate_task_to_member(member_id=query-rewriting-agent, task=Generate ┃
┃ five semantically similar ┃
┃ reformulations of the query: 'What is Small Intestine Cancer?') ┃
┃ ┃
┃ • delegate_task_to_member(member_id=query-rewriting-agent, task=Generate ┃
┃ five semantically similar ┃
┃ reformulations of the query: 'What are Small Intestine Cancers?') ┃
┃ ┃
┃ • delegate_task_to_member(member_id=retrieval-agent, task=Retrieve ┃
┃ information on Small Intestine Cancer from ┃
┃ the knowledge base.) ┃
┃ ┃
┃ • delegate_task_to_member(member_id=critique-agent, task=Review the ┃
┃ retrieved passages related to Small ┃
┃ Intestine Cancer from MedQuAD context and evaluate for relevance and ┃
┃ coverage. Confirm if additional ┃
┃ retrieval is needed to comprehensively answer the user's query.) ┃
┃ ┃
┃ • delegate_task_to_member(member_id=retrieval-agent, task=Conduct a more ┃
┃ focused search in the knowledge base ┃
┃ to obtain detailed information on Small Intestine Cancer, including its ┃
┃ definition, symptoms, treatment ┃
┃ options, and prognosis.) ┃
┃ ┃
┃ • delegate_task_to_member(member_id=response-generation-agent, task=Using ┃
┃ the retrieved passage on Small ┃
┃ Intestine Cancer from MedQuAD context 0, generate a comprehensive response ┃
┃ that defines Small Intestine ┃
┃ Cancer, its types, symptoms, treatment options, and prognosis. The ┃
┃ response should cover what small ┃
┃ intestine cancer is, associated risk factors, diagnosis, and available ┃
┃ treatment practices.) ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
┏━ Response (50.2s) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ ┃
┃ Small Intestine Cancer is a type of cancer occurring in the small intestine, ┃
┃ part of the digestive system that connects the stomach to the large ┃
┃ intestine. It plays a key role in extracting nutrients from food and passing ┃
┃ waste material. The small intestine encompasses the duodenum, jejunum, and ┃
┃ ileum. ┃
┃ ┃
┃ Types of Small Intestine Cancer include adenocarcinoma, sarcoma (such as ┃
┃ leiomyosarcoma), carcinoid tumors, gastrointestinal stromal tumors, and ┃
┃ lymphoma. Adenocarcinoma starts in glandular cells lining the small ┃
┃ intestine and is the most common type. It typically occurs near the stomach ┃
┃ and can grow to block the intestine. Leiomyosarcoma originates in the smooth ┃
┃ muscle cells, often near the large intestine. ┃
┃ ┃
┃ Risk factors vary, but a risk factor does not guarantee cancer development. ┃
┃ Diagnosis and staging usually involve simultaneous testing, and the ┃
┃ prognosis and treatment options depend on the cancer type and tumor ┃
┃ resectability. Treatments include surgery, chemotherapy, radiation, and ┃
┃ clinical trials, which offer newer treatment avenues. ┃
┃ ┃
┃ This overview provides a detailed look at Small Intestine Cancer, including ┃
┃ types, risks, diagnosis, and treatments based on clinical advancements ┃
┃ [Source: PMID: 26389461]. ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
Ce que ce design offre
On obtient ainsi un pipeline RAG qui s’interroge avant de parler : la récupération, la critique et la génération constituent des étapes distinctes pouvant être examinées individuellement, au lieu d’une seule opération opaque. Pour y parvenir, il a fallu imbriquer des Agno Teams afin d’effectuer des améliorations itératives, assembler une véritable recherche hybride à partir de vecteurs denses, spars et issus d’interactions tardives dans Qdrant, et s’occuper de petits détails tels que les clés de charge utile, les noms des vecteurs et la manière dont le contexte est partagé entre les agents. S’attendre à ce que les premières tentatives échouent, car c’est sur ces petits détails que se concentre le plus clair du temps de débogage.
Lectures complémentaires
- Utiliser Codex dans VS Code : portée, points de récupération et solutions aux pannes fréquentes — Un guide pratique pour l’extension Codex VS Code : installation, connexion, première tâche d’agent délimitée, utilisation en cloud versus via la ligne de commande, configuration partagée, ainsi que solutions pour WSL, approbations et authentification à distance.
- Orchestration multi-agent sur Bedrock et LangGraph : quatre modèles — Modèles superviseur-travailleur, pipeline, diffusion et débat avec LangGraph sur AWS Bedrock, ainsi que mécanismes de transfert, de contrôle budgétaire, de suivi et de gestion des pannes en production.