feat: solution for 'Повторный экзамен: FAQ-бот — ChromaDB + один MCP-tool'

This commit is contained in:
2026-07-01 15:04:34 +03:00
parent e42f7eac1e
commit f522dcfa80
7 changed files with 223 additions and 289 deletions
+22
View File
@@ -0,0 +1,22 @@
import os
from pydantic import BaseSettings
class Settings(BaseSettings):
# ChromaDB configuration
chroma_db_path: str = "./chroma_db"
chroma_collection_name: str = "faq_collection"
# Ollama embedding configuration
ollama_embed_model: str = "all-MiniLM-L6-v2"
ollama_host: str = "http://localhost"
ollama_port: int = 11434
# OpenAI LLM configuration
openai_api_key: str = ""
openai_model: str = "gpt-3.5-turbo"
class Config:
env_file = ".env"
env_file_encoding = "utf-8"
settings = Settings()
+14
View File
@@ -0,0 +1,14 @@
from langchain_ollama import OllamaEmbeddings
from src.config import settings
# Instantiate the Ollama embeddings once for reuse
ollama_embeddings = OllamaEmbeddings(
model=settings.ollama_embed_model,
base_url=f"{settings.ollama_host}:{settings.ollama_port}"
)
def get_embedding(text: str):
"""
Return the embedding vector for a single text string.
"""
return ollama_embeddings.embed_query(text)
+42 -99
View File
@@ -1,113 +1,56 @@
import os
import json
from pathlib import Path
from dotenv import load_dotenv
from langchain.embeddings import OllamaEmbeddings
from langchain.llms import Ollama
from langchain.vectorstores import Chroma
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from langchain_openai import ChatOpenAI
from langchain.chains import RetrievalQA
from langchain.schema import Document
from src.vector_store import vector_store
from src.config import settings
# Load environment variables (e.g., OLLAMA_BASE_URL)
load_dotenv()
app = FastAPI(title="FAQ Bot with ChromaDB and Ollama Embeddings")
# Configuration
OLLAMA_MODEL = os.getenv("OLLAMA_MODEL", "llama3.1")
OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
# OpenAI LLM
llm = ChatOpenAI(
model=settings.openai_model,
openai_api_key=settings.openai_api_key,
temperature=0.0
)
# Initialize embeddings and LLM using Ollama
embeddings = OllamaEmbeddings(model=OLLAMA_MODEL, base_url=OLLAMA_BASE_URL)
llm = Ollama(model=OLLAMA_MODEL, base_url=OLLAMA_BASE_URL)
# RetrievalQA chain
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=vector_store.db.as_retriever()
)
# Initialize ChromaDB client and collection
chroma_client = Chroma(client_kwargs={"persist_directory": "./chromadb"})
collection_name = "faq_collection"
class AskRequest(BaseModel):
question: str
# Load or create the collection
vectorstore = chroma_client.get_or_create_collection(name=collection_name, embedding_function=embeddings)
class AskResponse(BaseModel):
answer: str
# Sample FAQ data (could be loaded from a file or database)
FAQ_DATA = [
{
"question": "What is the return policy?",
"answer": "You can return any item within 30 days of purchase with a receipt."
},
{
"question": "How do I track my order?",
"answer": "After placing an order, you will receive a tracking number via email."
},
{
"question": "Do you offer international shipping?",
"answer": "Yes, we ship to most countries worldwide. Shipping fees apply."
},
{
"question": "What payment methods are accepted?",
"answer": "We accept credit cards, debit cards, and PayPal."
},
{
"question": "How can I reset my password?",
"answer": "Click on 'Forgot password' at the login page and follow the instructions."
}
]
class AddRequest(BaseModel):
text: str
metadata: dict | None = None
def index_faq_data():
@app.post("/ask", response_model=AskResponse)
async def ask(request: AskRequest):
"""
Index FAQ questions into the Chroma collection.
Each question is stored with its answer as metadata.
Endpoint to ask a question to the FAQ bot.
"""
# Check if the collection already has documents
if vectorstore.count() > 0:
print(f"Collection '{collection_name}' already indexed with {vectorstore.count()} documents.")
return
try:
answer = qa_chain.run(request.question)
return AskResponse(answer=answer)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
texts = [item["question"] for item in FAQ_DATA]
metadatas = [{"answer": item["answer"]} for item in FAQ_DATA]
# Add documents to the collection
vectorstore.add_texts(texts=texts, metadatas=metadatas)
print(f"Indexed {len(texts)} FAQ entries into '{collection_name}'.")
def create_faq_chain():
@app.post("/add")
async def add(request: AddRequest):
"""
Create a RetrievalQA chain that uses the Chroma vector store and Ollama LLM.
Endpoint to add a new FAQ entry to the vector store.
"""
retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=retriever,
return_source_documents=True
)
return qa_chain
def main():
# Index data if not already indexed
index_faq_data()
# Create the FAQ chain
qa_chain = create_faq_chain()
print("\nFAQ Bot is ready! Type your question (or 'exit' to quit).")
while True:
user_input = input("\nYou: ").strip()
if user_input.lower() in {"exit", "quit"}:
print("Goodbye!")
break
# Get answer from the chain
result = qa_chain({"query": user_input})
answer = result.get("result", "Sorry, I couldn't find an answer.")
sources = result.get("source_documents", [])
print(f"\nBot: {answer}")
if sources:
print("\nSources:")
for doc in sources:
# Each doc is a Document with metadata containing the answer
source_answer = doc.metadata.get("answer", "No answer metadata.")
print(f"- {source_answer}")
if __name__ == "__main__":
main()
try:
doc = Document(page_content=request.text, metadata=request.metadata or {})
vector_store.add_documents([doc])
return {"status": "added"}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
+25 -92
View File
@@ -1,98 +1,31 @@
"""
Vector store implementation using ChromaDB.
from langchain_community.vectorstores import Chroma
from langchain.schema import Document
from src.config import settings
from src.embeddings import ollama_embeddings
This module creates a persistent ChromaDB collection named 'faq' and
indexes a predefined FAQ dataset. The collection is stored in the
directory specified by `persist_dir`.
The dataset is a list of dictionaries with 'question' and 'answer'
keys. The answers are stored as documents; the questions are stored
as metadata for easier retrieval.
"""
import os
from typing import List, Dict
import chromadb
from chromadb.config import Settings
# Predefined FAQ dataset
FAQ_DATA: List[Dict[str, str]] = [
{
"question": "What is the capital of France?",
"answer": "Paris is the capital of France.",
},
{
"question": "Who wrote '1984'?",
"answer": "George Orwell wrote '1984'.",
},
{
"question": "What is the boiling point of water?",
"answer": "The boiling point of water is 100°C at sea level.",
},
]
class DummyEmbedding:
class FAQVectorStore:
"""
Dummy embedding function that returns a fixed vector of zeros.
This avoids the need for an external embedding service during tests.
Wrapper around Chroma vector store for FAQ documents.
"""
def __call__(self, texts: List[str]) -> List[List[float]]:
# Return a vector of 768 zeros for each text
return [[0.0] * 768 for _ in texts]
def get_vector_store(persist_dir: str) -> chromadb.Collection:
"""
Create or load a ChromaDB collection named 'faq'.
Parameters
----------
persist_dir : str
Directory where the ChromaDB data will be persisted.
Returns
-------
chromadb.Collection
The loaded or newly created collection.
"""
# Ensure the persistence directory exists
os.makedirs(persist_dir, exist_ok=True)
# Initialize Chroma client with persistence
client = chromadb.Client(
Settings(
persist_directory=persist_dir,
)
)
# Check if the collection already exists
if "faq" in client.list_collections():
collection = client.get_collection(name="faq")
else:
# Create a new collection
collection = client.create_collection(name="faq")
# Prepare documents and metadata
documents = [entry["answer"] for entry in FAQ_DATA]
metadatas = [{"question": entry["question"]} for entry in FAQ_DATA]
ids = [f"faq_{i}" for i in range(len(FAQ_DATA))]
# Use dummy embeddings to embed the documents
dummy_embedder = DummyEmbedding()
embeddings = dummy_embedder(documents)
# Add documents to the collection
collection.add(
documents=documents,
metadatas=metadatas,
ids=ids,
embeddings=embeddings,
def __init__(self):
self.db = Chroma(
collection_name=settings.chroma_collection_name,
persist_directory=settings.chroma_db_path,
embedding_function=ollama_embeddings
)
# Persist the collection
client.persist()
def add_documents(self, documents: list[Document]):
"""
Add a list of Documents to the vector store and persist.
"""
self.db.add_documents(documents)
self.db.persist()
return collection
def similarity_search(self, query: str, k: int = 4):
"""
Retrieve the top-k most similar documents to the query.
"""
return self.db.similarity_search(query, k=k)
# Singleton instance for use in the application
vector_store = FAQVectorStore()