fix: main.py

main.py

@@ -1,18 +1,21 @@
 import os
 import asyncio
+from pathlib import Path
 from dotenv import load_dotenv
+
 from langchain_openai import ChatOpenAI, OpenAIEmbeddings
 from langchain_chroma import Chroma
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_core.documents import Document
+from langchain_tavily import TavilySearchResults
 from langchain.tools import tool
 from deepagents import create_deep_agent
 from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
 
-# Load environment variables
+# --------------------- 1. Загрузка переменных окружения ---------------------
 load_dotenv()
 
-# ---------- LLM and Embeddings ----------
+# --------------------- 2. LLM и Embeddings ---------------------
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
     base_url="https://openrouter.ai/api/v1",
@@ -26,85 +29,78 @@ embeddings = OpenAIEmbeddings(
     api_key=os.getenv("OPENAI_API_KEY"),
 )
 
-# ---------- Vector Store ----------
-CHROMA_DIR = "./chroma_db"
+# --------------------- 3. Векторное хранилище Chroma ---------------------
+CHROMA_DIR = Path("./chroma_db")
+CHROMA_DIR.mkdir(parents=True, exist_ok=True)
 vector_store = Chroma(
     collection_name="knowledge",
     embedding_function=embeddings,
-    persist_directory=CHROMA_DIR,
+    persist_directory=str(CHROMA_DIR),
 )
 
-# ---------- Document Loader ----------
-
-def load_documents(directory: str):
-    """Read .txt/.md files, split into chunks and add to Chroma."""
+# --------------------- 4. Загрузка документов ---------------------
+DOCS_DIR = Path("./documents")
+if DOCS_DIR.exists():
     splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    docs = []
-    for root, _, files in os.walk(directory):
-        for file in files:
-            if file.lower().endswith(('.txt', '.md')):
-                path = os.path.join(root, file)
-                with open(path, 'r', encoding='utf-8') as f:
-                    text = f.read()
-                chunks = splitter.split_text(text)
-                docs.extend([Document(page_content=c, metadata={"source": path}) for c in chunks])
-    if docs:
-        vector_store.add_documents(docs)
-        vector_store.persist()
+    for file_path in DOCS_DIR.rglob("*.txt"):
+        text = file_path.read_text(encoding="utf-8")
+        docs = splitter.split_text(text)
+        documents = [Document(page_content=chunk, metadata={"source": str(file_path)}) for chunk in docs]
+        vector_store.add_documents(documents)
+    vector_store.persist()
 
-# Load documents once at startup
-if not os.path.exists(CHROMA_DIR) or not os.listdir(CHROMA_DIR):
-    load_documents("./documents")
-
-# ---------- Tools ----------
+# --------------------- 5. Инструменты ---------------------
 @tool
 def search_local_kb(query: str, top_k: int = 3) -> str:
     """Semantic search in the local knowledge base."""
     docs = vector_store.similarity_search(query, k=top_k)
     if not docs:
-        return "No relevant information found in local knowledge base."
-    return "\n---\n".join(f"{d.metadata.get('source', 'unknown')}\n{d.page_content}" for d in docs)
+        return "No relevant local knowledge found."
+    return "\n---\n".join(f"{i+1}. {doc.page_content[:200]}..." for i, doc in enumerate(docs))
 
 @tool
 def web_search(query: str) -> str:
     """Web search using Tavily."""
-    from langchain_tavily import TavilySearchResults
-    tavily = TavilySearchResults(max_results=3)
+    tavily = TavilySearchResults(api_key=os.getenv("TAVILY_API_KEY"))
     results = tavily.run(query)
     if not results:
         return "No web results found."
-    return "\n---\n".join(f"{r['title']}\n{r['content']}" for r in results)
+    return "\n---\n".join(f"{i+1}. {res['title']}\n{res['url']}\n{res['content'][:200]}..." for i, res in enumerate(results))
 
-# ---------- Backend ----------
+# --------------------- 6. Backend ---------------------
 backend = CompositeBackend([
     LocalShellBackend(workspace_dir="./workspace"),
     FilesystemBackend(),
 ])
 
-# ---------- Agent ----------
+# --------------------- 7. Создание агента ---------------------
 agent = create_deep_agent(
     model=llm,
     tools=[search_local_kb, web_search],
     backend=backend,
-    system_prompt="You are a helpful assistant. For questions about local documents use the local knowledge base. For up‑to‑date facts use web search. Always state the source (chromadb or tavily) in your answer.",
+    system_prompt=(
+        "You are an assistant that answers user questions.\n"
+        "If the question is about information that should be in the local knowledge base, use the tool `search_local_kb`.\n"
+        "If the question requires up‑to‑date information from the web, use the tool `web_search`.\n"
+        "Always indicate the source of the answer in the format: `Источник: chromadb` or `Источник: tavily`."
+    ),
 )
 
-# ---------- Main Loop ----------
-async def main():
-    print("RAG Agent ready. Type 'exit' to quit.")
+# --------------------- 8. CLI ---------------------
+async def chat_loop():
+    print("Добро пожаловать в RAG‑агент. Введите 'exit' для выхода.")
     while True:
         user_input = input("\nЗапрос: ")
-        if user_input.lower() in {"exit", "quit"}:
-            print("Goodbye!")
+        if user_input.lower() in {"exit", "quit", "q"}:
+            print("До свидания!")
             break
-        # Invoke agent
         result = await agent.ainvoke(
-            {"messages": [HumanMessage(content=user_input)]},
+            {"messages": [{"role": "user", "content": user_input}]},
             {"configurable": {"thread_id": "session-1"}},
         )
-        # Extract last message content
-        answer = result["messages"][-1].content
-        print(f"\nОтвет:\n{answer}")
+        # Последнее сообщение агента
+        content = result["messages"][-1]["content"]
+        print(content)
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(chat_loop())