fix: main.py — Агент с RAG-памятью

main.py

@@ -1,77 +1,136 @@
-import asyncio
 import os
+import asyncio
 from pathlib import Path
-
-from langchain_core.messages import HumanMessage
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_core.documents import Document
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_qdrant import QdrantVectorStore
 from langchain.tools import tool
 from deepagents import create_deep_agent
 from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+from langchain_core.messages import HumanMessage
 
-from utils import llm, vector_store, splitter
-from langchain_core.documents import Document
+# Configuration
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+if not OPENAI_API_KEY:
+    raise RuntimeError("OPENAI_API_KEY not set in environment")
 
+# LLM via OpenRouter
+llm = ChatOpenAI(
+    model="openai/gpt-oss-20b:free",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=OPENAI_API_KEY,
+    temperature=0.0,
+)
+
+# Embeddings via OpenRouter
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=OPENAI_API_KEY,
+)
+
+# Qdrant client and vector store
+from qdrant_client import QdrantClient
+qdrant_client = QdrantClient(url="http://localhost:6333")
+collection_name = "knowledge_base"
+vector_store = QdrantVectorStore(
+    client=qdrant_client,
+    collection_name=collection_name,
+    embedding_function=embeddings,
+)
+
+# Text splitter
+splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+
+# Tool: search knowledge base
 @tool
 def search_knowledge_base(query: str, max_results: int = 3) -> str:
     """Search the knowledge base for relevant information."""
     docs = vector_store.similarity_search(query, k=max_results)
-    return "\n".join(d.page_content for d in docs) if docs else "No results."
+    if not docs:
+        return "No results found."
+    return "\n\n".join(f"Title: {doc.metadata.get('title', 'unknown')}\n{doc.page_content}" for doc in docs)
 
+# Tool: add to knowledge base
 @tool
-def add_to_knowledge_base(content: str, title: str = "doc") -> str:
+def add_to_knowledge_base(content: str, title: str = "document") -> str:
     """Add content to the knowledge base."""
     chunks = splitter.split_text(content)
     docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
     vector_store.add_documents(docs)
-    return f"Added {len(docs)} chunks for {title}."
+    return f"Added {len(docs)} chunks from '{title}'."
 
+# Backend for deepagents
 backend = CompositeBackend([
     LocalShellBackend(workspace_dir="./workspace"),
     FilesystemBackend(),
 ])
 
+# Agent
 agent = create_deep_agent(
     model=llm,
     tools=[search_knowledge_base, add_to_knowledge_base],
     backend=backend,
-    system_prompt="You are a helpful assistant with access to a knowledge base. Use the provided tools to search and add information.",
+    system_prompt="You are a helpful knowledge assistant. Use the provided tools to search and add information.",
 )
 
-async def main():
-    print("RAG Agent CLI. Commands: /add, /search, /quit")
+# Helper: load documents from a directory
+def load_documents_from_dir(directory: str):
+    dir_path = Path(directory)
+    if not dir_path.is_dir():
+        raise ValueError(f"Directory {directory} does not exist.")
+    for file_path in dir_path.rglob("*"):
+        if file_path.is_file() and file_path.suffix.lower() in {".txt", ".md", ".py", ".json"}:
+            content = file_path.read_text(encoding="utf-8")
+            title = file_path.stem
+            add_to_knowledge_base(content, title)
+
+# Interactive CLI
+async def interactive_loop():
+    print("RAG Agent CLI. Commands: /add <file_path>, /search <query>, /quit")
     while True:
         user_input = input(">> ").strip()
         if not user_input:
             continue
         if user_input.lower() == "/quit":
-            print("Goodbye.")
+            print("Exiting.")
             break
-        if user_input.lower().startswith("/add"):
-            title = input("Title: ").strip()
-            print("Enter content (end with a single line containing only END):")
-            lines = []
-            while True:
-                line = input()
-                if line.strip() == "END":
-                    break
-                lines.append(line)
-            content = "\n".join(lines)
+        if user_input.startswith("/add "):
+            _, file_path = user_input.split(maxsplit=1)
+            try:
+                content = Path(file_path).read_text(encoding="utf-8")
+                title = Path(file_path).stem
                 result = add_to_knowledge_base(content, title)
                 print(result)
+            except Exception as e:
+                print(f"Error adding file: {e}")
             continue
-        if user_input.lower().startswith("/search"):
-            query = input("Query: ").strip()
-            max_results_str = input("Max results (default 3): ").strip()
-            max_results = int(max_results_str) if max_results_str.isdigit() else 3
-            result = search_knowledge_base(query, max_results)
-            print("Search results:")
+        if user_input.startswith("/search "):
+            _, query = user_input.split(maxsplit=1)
+            result = search_knowledge_base(query, max_results=3)
             print(result)
             continue
-        # Regular message to agent
+        # Treat as normal message to agent
+        try:
             response = await agent.ainvoke(
                 {"messages": [HumanMessage(content=user_input)]},
                 {"configurable": {"thread_id": "session-1"}},
             )
             print(response["messages"][-1].content)
+        except Exception as e:
+            print(f"Agent error: {e}")
+
+def main():
+    # Optional: load initial docs from a folder
+    init_dir = os.getenv("INIT_DOCS_DIR")
+    if init_dir:
+        try:
+            load_documents_from_dir(init_dir)
+            print(f"Loaded documents from {init_dir}")
+        except Exception as e:
+            print(f"Failed to load initial docs: {e}")
+    asyncio.run(interactive_loop())
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    main()