fix(needs_fixes): 1 исправлений, 0 отстояно — main.py

main.py

@@ -1,73 +1,178 @@
+"""
+# main.py
+# FAQ bot using deepagents, ChromaDB and a single MCP‑style HTTP tool.
+# The agent decides whether to query the local knowledge base or the
+# external metadata service and annotates the answer with a `source` field.
+"""
 import os
+import asyncio
 import json
-import httpx
 from pathlib import Path
-from langchain_ollama import ChatOllama
+from typing import List, Dict
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
 from langchain_chroma import Chroma
-from langchain.embeddings import OllamaEmbeddings
+from langchain_core.documents import Document
-from langchain.schema import Document
+from langchain_core.messages import HumanMessage, SystemMessage
-from langchain.prompts import ChatPromptTemplate
+from langchain.tools import tool
-from langchain.chains import LLMChain
+from deepagents import create_deep_agent
+from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
 
-# 1. Load FAQ into Chroma
+# ---------------------------------------------------------------------------
+# Configuration
+# ---------------------------------------------------------------------------
+# Load API key from .env or environment variable
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+if not OPENAI_API_KEY:
+    raise RuntimeError("OPENAI_API_KEY not set")
 
-def load_faq_to_chroma(md_path: str, persist_dir: str = "./chroma_faq"):
+# LLM configuration – OpenRouter
-    from langchain.document_loaders import TextLoader
+llm = ChatOpenAI(
-    from langchain.text_splitter import RecursiveCharacterTextSplitter
+    model="openai/gpt-oss-20b:free",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=OPENAI_API_KEY,
+    temperature=0.0,
+)
 
-    loader = TextLoader(md_path)
+# Embeddings – OpenRouter
-    docs = loader.load()
+embeddings = OpenAIEmbeddings(
-    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    model="text-embedding-3-small",
-    texts = splitter.split_documents(docs)
+    base_url="https://openrouter.ai/api/v1",
-    embeddings = OllamaEmbeddings(model="nomic-embed-text")
+    api_key=OPENAI_API_KEY,
-    chroma = Chroma.from_documents(texts, embeddings, persist_directory=persist_dir)
+)
-    chroma.persist()
-    return chroma
 
-# 2. Search function
+# ---------------------------------------------------------------------------
+# ChromaDB setup
+# ---------------------------------------------------------------------------
+CHROMA_PATH = Path("./chroma_faq")
+CHROMA_COLLECTION = "faq_collection"
 
-def search_course_docs(query: str, k: int = 3):
+vector_store = Chroma(
-    chroma = Chroma(persist_directory="./chroma_faq", embedding_function=OllamaEmbeddings(model="nomic-embed-text"))
+    collection_name=CHROMA_COLLECTION,
-    results = chroma.similarity_search(query, k=k)
+    embedding_function=embeddings,
-    return [doc.page_content for doc in results]
+    persist_directory=str(CHROMA_PATH),
+)
 
-# 3. MCP-style tool
+# Load markdown files into Chroma if not already persisted
+if not CHROMA_PATH.exists() or not list(CHROMA_PATH.iterdir()):
+    def load_faq_to_chroma(md_dir: str = "data"):
+        md_path = Path(md_dir)
+        docs: List[Document] = []
+        for file in md_path.glob("*.md"):
+            text = file.read_text(encoding="utf-8")
+            docs.append(Document(page_content=text, metadata={"source": file.name}))
+        vector_store.add_documents(docs)
+        vector_store.persist()
 
-def fetch_course_meta(query: str):
+    load_faq_to_chroma()
-    # For demo, use static JSON file
+
-    meta_path = Path("meta.json")
+# ---------------------------------------------------------------------------
+# Tools
+# ---------------------------------------------------------------------------
+@tool
+def search_course_docs(query: str, k: int = 3) -> str:
+    """Search the local FAQ collection for relevant passages."""
+    docs = vector_store.similarity_search(query, k=k)
+    if not docs:
+        return "No relevant information found in the course materials."
+    return "\n\n---\n\n".join(d.page_content for d in docs)
+
+# MCP‑style tool – simple HTTP GET to a local JSON file
+# For the purpose of this assignment we use a static JSON file
+# located at ./meta/course_meta.json
+@tool
+def fetch_course_meta(query: str) -> str:
+    """Return metadata that matches the query from a local JSON file."""
+    meta_path = Path("./meta/course_meta.json")
     if not meta_path.exists():
-        return {"error": "Meta not found"}
+        return "Metadata file not found."
-    meta = json.loads(meta_path.read_text())
+    data = json.loads(meta_path.read_text(encoding="utf-8"))
-    # simple search by key
+    # Very naive matching: return any entry where the query is a substring
-    return meta.get(query, {})
+    matches = [item for item in data if query.lower() in item.get("title", "").lower()]
+    if not matches:
+        return "No matching metadata found."
+    return json.dumps(matches, indent=2)
 
-# 4. Agent logic
+# ---------------------------------------------------------------------------
+# Backend for deepagents
+# ---------------------------------------------------------------------------
+backend = CompositeBackend([
+    LocalShellBackend(workspace_dir="./workspace"),
+    FilesystemBackend(),
+])
 
-def answer_question(question: str):
+# ---------------------------------------------------------------------------
-    # Simple heuristic: if question contains "schedule" or "метаданные" use meta
+# Agent definition
-    if any(word in question.lower() for word in ["schedule", "расписание", "метаданные"]):
+# ---------------------------------------------------------------------------
-        source = "mcp_meta"
+# System prompt instructs the agent to choose the appropriate tool and
-        answer = fetch_course_meta(question)
+# to annotate the answer with a `source` field.
-    else:
+SYSTEM_PROMPT = (
-        source = "chroma"
+    "You are an FAQ assistant for a course.\n"
-        answer = search_course_docs(question, k=1)[0]
+    "If the user asks about course materials, use the `search_course_docs` tool.\n"
-    return {"answer": answer, "source": source}
+    "If the user asks about schedule or metadata, use the `fetch_course_meta` tool.\n"
+    "Respond in JSON format with two fields: `answer` (string) and `source` (either `chroma` or `mcp_meta`).\n"
+    "Do not call both tools unless absolutely necessary."
+)
 
-if __name__ == "__main__":
+agent = create_deep_agent(
-    # CLI with preset questions
+    model=llm,
-    preset = [
+    tools=[search_course_docs, fetch_course_meta],
-        "Что такое ChromaDB?",
+    backend=backend,
-        "Как подключить Ollama embeddings?",
+    system_prompt=SYSTEM_PROMPT,
-        "Когда будет расписание следующего занятия?"
+)
+
+# ---------------------------------------------------------------------------
+# CLI helpers
+# ---------------------------------------------------------------------------
+PRESET_QUESTIONS = [
+    "What topics are covered in the first lecture?",  # chroma
+    "How can I access the lecture slides?",          # chroma
+    "What is the schedule for the next week?",        # mcp_meta
 ]
-    for q in preset:
+
-        res = answer_question(q)
+async def run_interactive():
-        print(f"Q: {q}\nA: {res['answer']}\nSource: {res['source']}\n")
+    print("FAQ Bot – type your question (or 'exit' to quit).\n")
-    # interactive
     while True:
-        q = input("Ask a question (or 'exit'): ")
+        user_input = input("> ")
-        if q.lower() == "exit":
+        if user_input.lower() in {"exit", "quit"}:
             break
-        res = answer_question(q)
+        result = await agent.ainvoke(
-        print(f"A: {res['answer']} (source: {res['source']})")
+            {"messages": [HumanMessage(content=user_input)]},
+            {"configurable": {"thread_id": "session-1"}},
+        )
+        # The agent returns a list of messages; the last is the assistant
+        assistant_msg = result["messages"][-1].content
+        try:
+            data = json.loads(assistant_msg)
+            print(f"\nAnswer: {data['answer']}\nSource: {data['source']}\n")
+        except Exception:
+            print("\nUnexpected response format:\n", assistant_msg)
+
+async def run_presets():
+    for q in PRESET_QUESTIONS:
+        print(f"\nQuestion: {q}")
+        result = await agent.ainvoke(
+            {"messages": [HumanMessage(content=q)]},
+            {"configurable": {"thread_id": "session-1"}},
+        )
+        assistant_msg = result["messages"][-1].content
+        try:
+            data = json.loads(assistant_msg)
+            print(f"Answer: {data['answer']}\nSource: {data['source']}")
+        except Exception:
+            print("Unexpected response format:\n", assistant_msg)
+
+# ---------------------------------------------------------------------------
+# Entry point
+# ---------------------------------------------------------------------------
+if __name__ == "__main__":
+    import argparse
+
+    parser = argparse.ArgumentParser(description="FAQ Bot CLI")
+    parser.add_argument("--presets", action="store_true", help="Run preset questions")
+    args = parser.parse_args()
+
+    if args.presets:
+        asyncio.run(run_presets())
+    else:
+        asyncio.run(run_interactive())