Агентны RAG з камандамі Agno: перапісванне запытаў, цыкл крытыкі і Qdrant
Агентны RAG з камандай Agno: каардынатар перапісвае запыты, крытык паўтарае пошук, а адказы бяруцца толькі з адобранага кантэксту гібрыднага пошуку Qdrant.
Крыніцы: The Agent Coordinator Pattern: Orchestrating Query Rewriting, Retrieval, and Critique with Agno
Цыкл адзьяварэння-крытыкі межы агентамі лёгка ўскладзіць на дошцы з напісамі, але дзівная рэч — яго важка запрацаваць. Сістэма, якая опісваецца тут, працуе на Agno Teams і мае чатыры ролі: коордынатор, агент для перапісву запітаў, цыкл, які продовжае удосконаляць кантэкст, і агент адпаведзей, які дае адпаведзь толькі пасля таго, як падтрымліваюцыя доказы будуць достатнія. У основе лежыць гібрыдны метод адзьяварэння ў Qdrant, які спалохвае ўжоўтучныя вектары, метод BM25 і сынтэзу рангаў.
Як утворэна команда
У верхней частцы знаходзіцца коордынатор — Team у рэжыме coordinate. Ён сам не выканае жадных задач. Ён распадзяляе заведамы, чакае і перадае кожны рэзультат далей у ланцугу.
- Агент для перапісву запітаў берае первісны запыт і стварае тры-пяць семантычна схожых варыянтав. Разныя формулюванні выявляюць разныя фрагменты, а адна формуліровка рэдка калі знаходзіць усе значыцьныя даныя.
- Цыкл адзялена-крытычнага аналізу — гэта тое месца, дзе адбываецца справжня праца. Другі
Team, установлены ў рэжымtasksі обмежаны параметрамmax_iterations, размешчаецца ўнутрь коордынатора як адзін член. У яму агент адзялена выконвае гібрыдны пошук для кожнага варыанта ў Qdrant, сумешчаючы ўжоцьплненыя і розрэджаныя векторы з паслядзейным перэранкаваннем. Пасля таго агент крытычнага аналізу оцінюе тое, што было адзялена, па рэлевантнасці і паверхносці пакрыцця. Мяккая паверхносць пакрыцця прызначае запіт знову, але ў удосконаўанай форме, а хорашая паверхносць пакрыцця дае схваленне. Цыкл завершаецца, калі крытык стае задоволеным або выкараны бюджэт ітэрацый, хто бы тое ні быў першым. - Агент адпаведзі бачыць толькі схвалены кантэкст, ніколі нечысты выход адзялена. Ён адпавядае строго на адважаныя з таго матэрыялу даныя, пазначае, які абзац падтрымлівае якое тверджэнне, і чыста адзначае, калі кантэкст недастатковы.
- Абсолютна адказь вяртаецца назад праз коордынатора без будзь-яых змян чыста, без перапісвання чыра перагляду.
Чаму ствараць команду ўнутрь іншай каманды? Гэта перадае ідэю крытыкі і ціклу на механізм ітэрацый Агно, таму ў кодзе прыкладнага праграмы няма ручна створанага цыклу while. Коордынатор бачыць аднаго чыстага члена, а вся логіка павторных спроб застаецца ўнутрь таго члена.
Стварэнне базы знанняў
Ніяны агент не можа выявіць нічога, пакуль не будзе існаваць база знанняў, і правільна рэалізацыя гэтага аспекта мае такое ж значэнне, як і дызайн самага агента.
Набор дадзеных, які лежыць у ўсім гэтым, — гэта MedQuAD_Context_GroupedQA, які складаецца з апошніх 8 000 медычных тэкстаў, кожны з якіх супакоўваецца з групаванымі парамі запытання-адказ. Пры прыеме дадзеных застаецца толькі столбець context. Пары запытання-адказ застаюцца без змян у наборэ дадзеных, адколі эксперымент пераканальваецца на выявленне інфармацыі з суровых тэкстаў, а не на запамятовванне адказаў.
Няма частакавання. Усій кантэкст кожнай строкі ўключаецца і зберагаецца як адна точка Qdrant. Гэта простае для розумення, але мае наследкамі — неабходна залежнасць ад власнага функцыянару обрыву дадзейнаў аптэкаў умяшчэння для дужа дзяўялых кантэкстаў.
Кожная точка мае тры вектары, кожны з якіх знаходзіцца у сваёй сабе іменаванай ўпоркі, што дае адну колекцыю з трыма взаімадопамагаючыміся відбірамі таго ж тэксту:
dense: умяшчэнне Gemini з 768 выміраміsparse: BM25 чырэз FastEmbedlate_interaction: мультывектар ColBERT, які выкорыстоўваецца для пераранжавання, а не для першага адбору
На завершанне ідзе кантракт пэйлоаду. Інтэграцыя Agno з Qdrant чакае пэўныя ключы пэйлоаду (name, content, meta_data і content_id), каб магчыма было перзбудаваць ўсероўнішыя об’екты Document у час адбору дадзейнаў.
Код праекту
Файлы знаходзяцца ў маленькай дрэве:
.
├── data_ingester.py
├── in-context-learning-agentic-team.py
├── pyproject.toml
├── .env
└── uv.lock
Спачатку выканана глобальная настройка, якая абарачвае імпорты, мадэль і об’ект знання:
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,
)
Перапісувальнік запітаў
Штучны інтэлект не мае жадных інструментаў, толькі мову. Пры отрыманні запіта ён стварае тры-пяць варыянтав, якія разлічаюцца за формулюваннем, конкрэтнасцю і сінонімамі. Мета — распаставаць шчыльнейшую сетку перш чым пачнёцца пошук.
# ---------------------------------------------------------------------------
# 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,
)
Агент для адаптавання
Сярод усіх агентоў гэты агент запытвае Qdrant безпосерэдна. Кожны варыант запыту практыкуе спалучаны метод пошуку тыпу «шчыльна-з розрывамі», а рэзультаты повертаюцца з анотаціямі пра тое, звядзе каналі ўзятыя і які у ніх рэйтынг; за патрэбы ёсць можлівасць паўтарнага адсортавання рэзультатаў пасля вялікага колькасці взаімадзеянняў. У яго інструкцыях сказана адзвярнуцца, што «нічога не знайдзена», і ніколі не ствараць правдападобна звучаючага тэксту.
# ---------------------------------------------------------------------------
# 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,
)
Агент крытыкі
Скептык у групе сам не адпавядае. Ён оцінюе, насколькі рэлевантнымі і повнамі ёсць рэзультаты, якія знайшоў агент збору інфармацыі, а потым альбо затверджвае кантэкст, альбо вяртае яго з паслявыявленнем прычыны. Самэ гэта ператварае падход «знайсці раз і спадзявацца» на справжній цыкл зворачнай свярзанасці.
# ---------------------------------------------------------------------------
# 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.",
],
)
Агент адказу
Толькі гэты агент размовляе з выкарыстоўцам. Ён чытае кантэкст, які ўжо затвердзіў крытык, падкрэпляе кожны тверджэнне цітатамі з яго і, калі не можа даты адказ, выдае чыстае паведамленне пра «недастатак кантэксту», а не няверна спадзяецца.
# ---------------------------------------------------------------------------
# 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,
)
Коордынатар
Называць яго агентам — значыць ператвараць значэнне гэтага слова, адколькі ён больш супаменяе дырыганта. Ён знае парадак (перапісваць, адзёрваць і адгукнуцца, адпаведзець) і перадае рэзультаты без ўсмяркавання іх. Весья логіка выконваецца пасля, а коордынатар толькі стараецца, каб усё відбывалася у правым парадку.
# ---------------------------------------------------------------------------
# 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,
)
Яго запуск
Скрыпт абсарбавання спаўнае межу между наборам дадзеных, трымаі эмбэдэрамі і 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()
Галоўны скрыпт складае агентаў і каманду:
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,
)
Паўна рэжыма працы стварае дзейнік з дакументамі, якія былі вышуканы, а таксама з панелямі паведамленняў кожнага агента:
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]. ┃
┃ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
Што дае гэты дызайн
У выніку аплікуюцца праграмныя каналы RAG, якія спачатку пераканаюць сябе, прытымкі да выдачы рэзультатаў: запошук, аналіз і стварэнне тэксту — гэта адзінаковыя этапы, кожны з якіх можна пераглядзець, а не адна незрозумелая процедура. Для досягнення гэтага патрэбна іерархія агентав Agno Teams для парадоксальнага удосконалення, стварэнне справжняга гібрыднага пошуку з ўжоцьплненых, розрозненых і вектараў пазнейшай взаімадзеі ў Qdrant, а таксама увага да дробных дэталяў, такіх як ключы пакета дадзеных, назвы вектараў і спосабы абмены кантэкстам між агентамі. Чакайце, што першыя спробы зазнаюць няўдач, адтак саме на гэтыя дробныя дэталі затрачаецца большая частка часу на адлучэнне бягаў.
Супаўзяныя матэрыялы
- Існаванне Codex у VS Code: дыячынства, пункты вякнаўлення і способы выправлення частых працоўных суперашчэкаў — практычны парадок па выкарыстоўванню расшырэння Codex у VS Code: інсталяцыя, заходжанне, першая задача для агента, праца з хмарам протыраці CLI, спяльнае налашчэнне, а таксама способы выправлення проблем у WSL, апраўленні і аўтэнтыфікацыя з даляйнасці.
- Оркестрацыя калькольнікаў агентаў на Bedrock і LangGraph: чатыры шаблону — шаблону керавальніка-рабочага, пайплайну, розпаду і дыскусіі з выкарыстоўваннем LangGraph на AWS Bedrock, а таксама механізмы перадачы задач, контролю бюджэту, трэйсінгу і способы выправлення працоўных суперашчэкаў у працэсе.