Agentic RAG z Agno Teams: przepisywanie zapytań, pętla krytyczna i Qdrant
Agentic RAG z zespołem Agno: koordynator przepisuje zapytania, krytyk powtarza proces pozyskiwania informacji, a odpowiedzi pochodzą wyłącznie z zatwierdzonego kontekstu w hybrydowym wyszukiwaniu Qdrant.
Źródła: The Agent Coordinator Pattern: Orchestrating Query Rewriting, Retrieval, and Critique with Agno
Pętla pozyskiwania informacji i ich krytyki pomiędzy agentami jest łatwa do narysowania na tablicy, ale zaskakująco trudna do uruchomienia. Opisany tutaj system działa w Agno Teams i ma cztery role: koordynatora, agenta przepisywania zapytań, pętlę, która ciągle udoskonala kontekst, oraz agenta odpowiedzi, który odpowiada dopiero wtedy, gdy dostępne dowody są wiarygodne. U podstaw funkcjonuje hybrydowe pozyskiwanie informacji w Qdrant, łączące gęste wektory, metodę BM25 oraz fuzję rankingu wzajemnego.
Struktura zespołu
Na szczycie znajduje się koordynator, czyli Team w trybie coordinate. Sam nie wykonywa żadnych zadań – rozdaje zadania, czeka i przekazuje każdy wynik dalej w łańcuchu.
- Agent przepisywania zapytań bierze surowe pytanie i tworzy od trzech do pięciu semantycznie podobnych wariantów. Różne sformułowania przywołują różne fragmenty tekstu, a jedno określenie rzadko pozwala znaleźć wszystko, co jest istotne.
- Pętla pozyskiwania i oceny to miejsce, gdzie odbywa się prawdziwa praca. Drugi
Team, ustawiony na trybtasksi ograniczony wartościąmax_iterations, jest umieszczany wewnątrz koordynatora jako pojedynczy członek. W jego obrębie agent pozyskiwania przeprowadza hybrydowe wyszukiwanie dla każdej wariantu w Qdrant, łącząc wektory gęste i rzadkie przy użyciu metody ponownego rankowania w późnym etapie interakcji. Następnie agent oceny ocenia uzyskane wyniki pod kątem istotności i zakresu pokrycia. Niewystarczające pokrycie powoduje ponowne wysłanie zapytania w udoskonalonej formie, natomiast dobre pokrycie zapewnia zatwierdzenie. Cykl kończy się, gdy agent oceny jest zadowolony lub wyczerpuje się budżet iteracji – to, co nastąpi pierwsze. - Agent odpowiedzi widzi tylko zatwierdzony kontekst, nigdy surowy wynik pozyskiwania. Odpowiada wyłącznie na podstawie tego materiału, wskazuje, który fragment potwierdza daną twierdzenie, oraz jasno informuje, gdy kontekst jest niewystarczający.
- Ostateczna odpowiedź wraca w górę przez koordynatora bez żadnych zmian, bez przepisywania ani ponownej oceny.
Dlaczego umieszczać zespół wewnątrz zespołu? Pozwala to przenieść koncepcję krytyki i pętli na własny mechanizm iteracji Agno, dzięki czemu w kodzie aplikacji nie ma ręcznie napisanych pętli while. Koordynator widzi jeden czysty element, a cała logika ponownych prób pozostaje wewnątrz tego elementu.
Budowanie bazy wiedzy
Żaden agent nie może nic pobrać, dopóki nie istnieje baza wiedzy, a prawidłowe ukształtowanie tej części jest równie ważne jak projekt agenta.
Podstawą jest zbiór danych MedQuAD_Context_GroupedQA, zawierający około 8 000 medycznych tekstów, z których każdy ma sparowane grupy pytań i odpowiedzi. Podczas przetwarzania zachowuje się tylko kolumnę context. Pary pytań i odpowiedzi pozostają nienaruszone w zbiorze danych, ponieważ eksperyment sprawdza możliwość wyszukiwania w surowych tekstach, a nie zapamiętywanie odpowiedzi.
Nie ma dzielenia na fragmenty. Pełny kontekst każdego wiersza jest włączany i przechowywany jako jeden punkt Qdrant. Jest to prostsze do zrozumienia, ale wiąże się z koniecznością polegania na własnych mechanizmach skracania kontekstu przez API do obsługi długich treści.
Każdy punkt zawiera trzy wektory, z których każdy znajduje się w osobnej, nazwanej pozycji, co daje jedną kolekcję z trzema uzupełniającymi się wersjami tego samego tekstu:
dense: wektor 768-wymiarowy z technologii Geminisparse: metody BM25 oraz FastEmbedlate_interaction: wektor wielowektorowy z ColBERT, używany do ponownego sortowania, a nie do pierwszego wyszukiwania
Ostatni element to specyfikacja treści przekazywanej do przechowywania. Integracja Agno z Qdrant wymaga określonych kluczy treści (name, content, meta_data i content_id), aby móc odtworzyć swoje wewnętrzne obiekty Document w momencie wyszukiwania.
Kod projektu
Pliki znajdują się w małym drzewie:
.
├── data_ingester.py
├── in-context-learning-agentic-team.py
├── pyproject.toml
├── .env
└── uv.lock
Konfiguracja globalna jest pierwsza i obejmuje importy, model oraz obiekt wiedzy:
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,
)
Przerabiacz zapytań
Ten agent nie posiada żadnych narzędzi, jedynie umiejętności językowe. Na podstawie zadanej pytania tworzy od trzech do pięciu wariantów, które różnią się sformułowaniem, precyzją i synonimami. Celem jest rozszerzenie zakresu poszukiwań przed ich rozpoczęciem.
# ---------------------------------------------------------------------------
# 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 pobierający
Wśród wszystkich agentów to właśnie on żąda danych bezpośrednio od Qdrant. Każda wersja zapytania jest przetwarzana za pomocą metody poszukiwania typu dense-plus-sparse, a wyniki są zwracane z adnotacjami wskazującymi, skąd pochodzą oraz jaki mają wynik oceny; w razie potrzeby dostępny jest dodatkowy mechanizm ponownego rankowania po interakcji. Zgodnie z instrukcjami należy zgłosić „nic nie znaleziono” i nigdy nie tworzyć wiarygodnie brzmiących fragmentów tekstu.
# ---------------------------------------------------------------------------
# 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,
)
Agent krytyczny
Sceptyk w grupie sam nie odpowiada. Ocenia, na ile to, co znalazł agent wyszukiwawczy, jest istotne i kompleksowe, a następnie albo zatwierdza kontekst, albo odsyła go z uzasadnieniem. To właśnie sprawia, że podejście „wyszukaj raz i miej nadzieję” staje się prawdziwym pętlą sprzężenia zwrotnego.
# ---------------------------------------------------------------------------
# 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 odpowiedzi
Tylko ten agent rozmawia z użytkownikiem. Czyta kontekst, który został już zatwierdzony przez recenzenta, opiera każde twierdzenie w nim na cytatach i w razie potrzeby wyświetla wyraźną wiadomość o „niewystarczającym kontekście”, zamiast zgadywać.
# ---------------------------------------------------------------------------
# 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,
)
Koordynator
Nazywanie go agentem to przesada, ponieważ bardziej przypomina dyrygenta. Zna kolejność działań (przepisanie, pobranie i ocena, odpowiedź) oraz przekazuje wyniki bez ich edycji. Wszystkie rozważania odbywają się później, a koordynator jedynie dopilnuje, aby wszystko działo się we właściwej kolejności.
# ---------------------------------------------------------------------------
# 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,
)
Uruchamianie
Skrypt integracji łączy zestaw danych, trzy narzędzia do generowania embedów oraz 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()
Główny skrypt łączy agenty i zespół:
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,
)
Pełny przebieg generuje długi ślad, zawierający wyszukiwania dokumentów oraz panele wiadomości każdego agenta:
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]. ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
Co daje ten projekt
W rezultacie powstaje pipeline RAG, który najpierw sam siebie testuje przed wydaniem odpowiedzi: pozyskiwanie danych, ich analiza i generowanie to odrębne etapy, które można sprawdzić osobno, zamiast jednej nieprzejrzystej operacji. Aby to osiągnąć, konieczne było użycie Agno Teams do iteracyjnego udoskonalania rozwiązania, stworzenie prawdziwego hybrydowego systemu wyszukiwania na podstawie gęstych, rzadkich oraz wektorów z późną interakcją w Qdrant, a także skupienie się na drobnych szczegółach, takich jak klucze danych, nazwy wektorów oraz sposób udostępniania kontekstu pomiędzy agentami. Oczekujmy, że pierwsze próby zawiodą, ponieważ to właśnie na tych drobnych szczegółach spędza się najwięcej czasu podczas debugowania.
Literatura pokrewna
- Używanie Codex w VS Code: zakres działania, punkty odzyskiwania oraz rozwiązania typowych problemów — Praktyczny przewodnik po rozszerzeniu Codex dla VS Code: instalacja, logowanie, pierwsze zadanie dla agenta, różnice między chmurą a interfejsem wiersza poleceń, wspólna konfiguracja oraz rozwiązania problemów z WSL, procedury zatwierdzania i autoryzacji zdalnej.
- Orkiestracja wielu agentów na Bedrock i LangGraph: cztery wzorce — Wzorce supervisor-worker, pipeline, fan-out oraz debate z wykorzystaniem LangGraph na AWS Bedrock, wraz z mechanizmami przekazywania zadań, kontrolą budżetu, śledzeniem działania oraz sposobami radzenia sobie z awariami w środowisku produkcyjnym.