fix: main.py — Повторный экзамен: FAQ-бот — ChromaDB + один MCP-tool

main.py

@@ -2,20 +2,18 @@ import os
 import asyncio
 import json
 from pathlib import Path
-from dotenv import load_dotenv
 
 from langchain_openai import ChatOpenAI, OpenAIEmbeddings
 from langchain_chroma import Chroma
 from langchain_core.documents import Document
 from langchain.tools import tool
+from langchain_text_splitter import RecursiveCharacterTextSplitter
+
 from deepagents import create_deep_agent
 from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
 from langchain_core.messages import HumanMessage
 
-# Загрузка переменных окружения
-load_dotenv()
-
-# Настройка LLM и эмбеддингов через OpenRouter
+# ---------- LLM ----------
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
     base_url="https://openrouter.ai/api/v1",
@@ -23,63 +21,7 @@ llm = ChatOpenAI(
     temperature=0.0,
 )
 
-embeddings = OpenAIEmbeddings(
-    model="text-embedding-3-small",
-    base_url="https://openrouter.ai/api/v1",
-    api_key=os.getenv("OPENAI_API_KEY"),
-)
-
-# Инициализация Chroma
-vector_store = Chroma(
-    collection_name="faq_collection",
-    embedding_function=embeddings,
-    persist_directory="./chroma_faq",
-)
-
-# Загрузка FAQ из markdown файлов в Chroma
-def load_faq_to_chroma() -> None:
-    data_dir = Path("data")
-    if not data_dir.exists():
-        return
-    docs = []
-    for md_file in data_dir.glob("*.md"):
-        content = md_file.read_text(encoding="utf-8")
-        title = md_file.stem
-        docs.append(Document(page_content=content, metadata={"title": title}))
-    if docs:
-        vector_store.add_documents(docs)
-
-# Tool: поиск по базе знаний
-@tool
-def search_course_docs(query: str, k: int = 3) -> str:
-    """Search the knowledge base for relevant information."""
-    docs = vector_store.similarity_search(query, k=k)
-    return "\n".join(d.page_content for d in docs) if docs else "No results."
-
-# Tool: получение метаданных курса (MCP-стиль)
-@tool
-def fetch_course_meta(query: str) -> str:
-    """Fetch course metadata from local JSON."""
-    meta_path = Path("meta.json")
-    if not meta_path.exists():
-        return "Metadata file not found."
-    data = json.loads(meta_path.read_text(encoding="utf-8"))
-    # Простая фильтрация по ключевому слову в запросе
-    if "schedule" in query.lower():
-        return json.dumps(data.get("schedule", []), indent=2)
-    if "instructor" in query.lower():
-        return data.get("instructor", "Unknown")
-    return json.dumps(data, indent=2)
-
-# Системный промпт агента
-system_prompt = (
-    "You are a helpful FAQ bot. Use only one tool per query. "
-    "If the question is about course materials, use search_course_docs. "
-    "If about schedule or metadata, use fetch_course_meta. "
-    "Indicate source in answer: source: chroma | mcp_meta."
-)
-
-# Backend для deepagents
+# ---------- Backend ----------
 backend = CompositeBackend(
     [
         LocalShellBackend(workspace_dir="./workspace"),
@@ -87,7 +29,74 @@ backend = CompositeBackend(
     ]
 )
 
-# Создание агента
+# ---------- Embeddings ----------
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+)
+
+# ---------- Vector Store ----------
+vector_store = Chroma(
+    collection_name="faq",
+    embedding_function=embeddings,
+    persist_directory="./chroma_faq",
+)
+
+# ---------- Load FAQ into Chroma ----------
+def load_faq_to_chroma() -> None:
+    """Read .md files from data/ and add them to the Chroma collection."""
+    data_dir = Path("data")
+    if not data_dir.exists():
+        return
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    docs = []
+    for md_file in data_dir.glob("*.md"):
+        content = md_file.read_text(encoding="utf-8")
+        chunks = splitter.split_text(content)
+        for i, chunk in enumerate(chunks):
+            docs.append(
+                Document(
+                    page_content=chunk,
+                    metadata={"source": md_file.name, "chunk": i},
+                )
+            )
+    if docs:
+        vector_store.add_documents(docs)
+        vector_store.persist()
+
+# ---------- Tools ----------
+@tool
+def search_course_docs(query: str, k: int = 3) -> str:
+    """Search the knowledge base for relevant information."""
+    docs = vector_store.similarity_search(query, k=k)
+    return "\n\n".join(d.page_content for d in docs) if docs else "No results found."
+
+# Load meta data once
+META_PATH = Path("meta.json")
+if META_PATH.exists():
+    META_DATA = json.loads(META_PATH.read_text(encoding="utf-8"))
+else:
+    META_DATA = {}
+
+@tool
+def fetch_course_meta(query: str) -> str:
+    """Return course metadata (schedule, etc.)."""
+    # Simple lookup: return the whole meta if query matches a key
+    for key, value in META_DATA.items():
+        if key.lower() in query.lower():
+            return f"{key}: {value}"
+    # Fallback: return all metadata
+    return json.dumps(META_DATA, indent=2)
+
+# ---------- Agent ----------
+system_prompt = (
+    "You are a helpful FAQ bot. Use search_course_docs for questions about course materials. "
+    "Use fetch_course_meta for questions about schedule or metadata. "
+    "Do not call both tools unless necessary. "
+    "In your answer, indicate source: chroma or mcp_meta."
+)
+
 agent = create_deep_agent(
     model=llm,
     tools=[search_course_docs, fetch_course_meta],
@@ -95,44 +104,38 @@ agent = create_deep_agent(
     system_prompt=system_prompt,
 )
 
-# Предварительная загрузка FAQ
-load_faq_to_chroma()
-
-# Предустановленные вопросы
-preset_questions = [
-    "Где находятся материалы по лекции 3?",
-    "Как изменить пароль?",
-    "Какой график занятий на следующую неделю?",
+# ---------- CLI ----------
+PRESET_QUESTIONS = [
+    "What topics are covered in the introductory module?",
+    "Explain the advanced algorithm discussed in chapter 3.",
+    "What is the schedule for the next semester?",
 ]
 
-async def main() -> None:
-    print("FAQ Bot CLI")
-    print("1-3: Предустановленные вопросы")
-    print("4: Ввести собственный вопрос")
-    print("5: Выход")
-    while True:
-        choice = input("Выберите вариант (1-5): ").strip()
-        if choice == "5":
-            print("До свидания!")
-            break
-        if choice in {"1", "2", "3"}:
-            question = preset_questions[int(choice) - 1]
-        elif choice == "4":
-            question = input("Введите ваш вопрос: ").strip()
-            if not question:
-                print("Пустой вопрос, попробуйте снова.")
-                continue
-        else:
-            print("Неверный выбор, попробуйте снова.")
-            continue
-
-        print(f"Вопрос: {question}")
+async def run_preset():
+    for q in PRESET_QUESTIONS:
         result = await agent.ainvoke(
-            {"messages": [HumanMessage(content=question)]},
+            {"messages": [HumanMessage(content=q)]},
             {"configurable": {"thread_id": "session-1"}},
         )
-        answer = result["messages"][-1].content
-        print(f"Ответ:\n{answer}\n")
+        print("\nQuestion:", q)
+        print("Answer:", result["messages"][-1].content)
+
+async def interactive_loop():
+    print("\nEnter your question (type 'exit' to quit):")
+    while True:
+        user_input = input("> ")
+        if user_input.lower() in ("exit", "quit"):
+            break
+        result = await agent.ainvoke(
+            {"messages": [HumanMessage(content=user_input)]},
+            {"configurable": {"thread_id": "session-1"}},
+        )
+        print("Answer:", result["messages"][-1].content)
+
+async def main():
+    load_faq_to_chroma()
+    await run_preset()
+    await interactive_loop()
 
 if __name__ == "__main__":
     asyncio.run(main())