fix(needs_fixes): 3 исправлений, 0 отстояно — main.py

main.py

@@ -1,36 +1,16 @@
-"""
-# main.py – RAG‑agent with Qdrant, OpenRouter, and deepagents
-# ----------------------------------------------------------
-# 1.  Imports and configuration
-# 2.  Qdrant vector store wrapper (embedding, add, search)
-# 3.  Text splitter (RecursiveCharacterTextSplitter)
-# 4.  LangChain tools: search_knowledge_base, add_to_knowledge_base
-# 5.  DeepAgent creation (create_deep_agent)
-# 6.  CLI client for /add, /search, /quit
-# ----------------------------------------------------------
-"""
 import os
 import asyncio
-import json
 from pathlib import Path
-from typing import List
+from langchain_openai import ChatOpenAI
-
+from langchain_ollama import OllamaEmbeddings
-from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_qdrant import QdrantVectorStore
 from langchain_core.documents import Document
-from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain.tools import tool
 from deepagents import create_deep_agent
 from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
-from langchain_qdrant import QdrantVectorStore
+from langchain_core.messages import HumanMessage
 
-# ------------------------------------------------------------------
+# ---------- LLM ----------
-# 1. Configuration
-# ------------------------------------------------------------------
-# Load environment variables (e.g. OPENAI_API_KEY)
-from dotenv import load_dotenv
-load_dotenv()
-
-# LLM – OpenRouter (free tier)
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
     base_url="https://openrouter.ai/api/v1",
@@ -38,110 +18,91 @@ llm = ChatOpenAI(
     temperature=0.0,
 )
 
-# Embeddings – OpenAI via OpenRouter
+# ---------- Embeddings ----------
-embeddings = OpenAIEmbeddings(
+# Using Ollama embeddings as per assignment correction
-    model="text-embedding-3-small",
+embeddings = OllamaEmbeddings(model="nomic-embed-text")
-    base_url="https://openrouter.ai/api/v1",
-    api_key=os.getenv("OPENAI_API_KEY"),
-)
 
-# Qdrant client – assumes Qdrant is running locally on default port
+# ---------- Vector Store (Qdrant) ----------
-qdrant_url = os.getenv("QDRANT_URL", "http://localhost:6333")
+# Ensure Qdrant is running locally (default port 6333)
-collection_name = "knowledge_base"
 vector_store = QdrantVectorStore(
-    url=qdrant_url,
+    url="http://localhost:6333",
-    collection_name=collection_name,
+    collection_name="knowledge",
-    embeddings=embeddings,
+    embedding_function=embeddings,
 )
 
-# Text splitter – 1000 chars max, 200 overlap
+# ---------- Tools ----------
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-
-# ------------------------------------------------------------------
-# 2. Tools
-# ------------------------------------------------------------------
 @tool
 def search_knowledge_base(query: str, max_results: int = 3) -> str:
-    """Semantic search in the Qdrant knowledge base."""
+    """Semantic search in the knowledge base."""
-    docs: List[Document] = vector_store.similarity_search(query, k=max_results)
+    docs = vector_store.similarity_search(query, k=max_results)
     if not docs:
-        return "No relevant documents found."
+        return "No results found."
-    return "\n\n---\n\n".join([f"{doc.metadata.get('title', 'Untitled')}:\n{doc.page_content}" for doc in docs])
+    return "\n---\n".join(f"{i+1}. {doc.page_content[:200]}..." for i, doc in enumerate(docs))
 
 @tool
-def add_to_knowledge_base(content: str, title: str = "Untitled") -> str:
+def add_to_knowledge_base(content: str, title: str = "untitled") -> str:
-    """Add a new document to the knowledge base.
+    """Add a document to the knowledge base."""
-    The content is split into chunks before being stored.
+    doc = Document(page_content=content, metadata={"title": title})
-    """
+    vector_store.add_documents([doc])
-    chunks = text_splitter.split_text(content)
+    return f"Document '{title}' added to the knowledge base."
-    docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
-    vector_store.add_documents(docs)
-    return f"Added {len(docs)} chunks for document '{title}'."
 
-# ------------------------------------------------------------------
+# ---------- Backend ----------
-# 3. DeepAgent setup
-# ------------------------------------------------------------------
 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 an assistant with access to a knowledge base. Use the provided tools to search and add information."
 )
 
-# ------------------------------------------------------------------
+# ---------- Document Loader ----------
-# 4. CLI client
+async def load_documents_from_dir(directory: str):
-# ------------------------------------------------------------------
+    """Load all text files from a directory into the vector store."""
-async def run_cli():
+    for file_path in Path(directory).rglob("*.txt"):
-    print("Welcome to the RAG Agent CLI. Commands: /add <title> <file>, /search <query>, /quit")
+        text = file_path.read_text(encoding="utf-8")
-    thread_id = "cli-session"
+        title = file_path.stem
+        await agent.ainvoke(
+            {"messages": [HumanMessage(content=f"/add {title}")], "content": text},
+            {"configurable": {"thread_id": "init"}},
+        )
+
+# ---------- Interactive CLI ----------
+async def interactive_loop():
+    print("Welcome to the RAG Agent. Commands: /add <title>, /search <query>, /quit")
     while True:
-        try:
         user_input = input("> ")
-        except EOFError:
+        if user_input.strip() == "/quit":
-            break
-        if not user_input:
-            continue
-        if user_input.startswith("/quit"):
             print("Goodbye!")
             break
-        if user_input.startswith("/add"):
+        if user_input.startswith("/add "):
-            parts = user_input.split(maxsplit=2)
+            parts = user_input.split(" ", 1)
-            if len(parts) < 3:
+            title = parts[1] if len(parts) > 1 else "untitled"
-                print("Usage: /add <title> <file_path>")
+            content = input("Enter content: ")
-                continue
-            title, file_path = parts[1], parts[2]
-            try:
-                content = Path(file_path).read_text(encoding="utf-8")
-            except Exception as e:
-                print(f"Error reading file: {e}")
-                continue
-            # Invoke tool directly
-            result = add_to_knowledge_base(content, title)
-            print(result)
-            continue
-        if user_input.startswith("/search"):
-            query = user_input[len("/search"):].strip()
-            if not query:
-                print("Usage: /search <query>")
-                continue
-            # Use agent to perform search via tool
             response = await agent.ainvoke(
-                {"messages": [{"role": "user", "content": f"search {query}"}]},
+                {"messages": [HumanMessage(content=f"/add {title}")], "content": content},
-                {"configurable": {"thread_id": thread_id}},
+                {"configurable": {"thread_id": "session"}},
             )
             print(response["messages"][-1].content)
-            continue
+        elif user_input.startswith("/search "):
-        # Default: treat as normal user message
+            query = user_input.split(" ", 1)[1]
             response = await agent.ainvoke(
-            {"messages": [{"role": "user", "content": user_input}]},
+                {"messages": [HumanMessage(content=f"/search {query}")]},
-            {"configurable": {"thread_id": thread_id}},
+                {"configurable": {"thread_id": "session"}},
             )
             print(response["messages"][-1].content)
+        else:
+            print("Unknown command. Use /add, /search, or /quit.")
+
+# ---------- Main ----------
+async def main():
+    # Optional: load initial documents
+    # await load_documents_from_dir("./data")
+    await interactive_loop()
 
 if __name__ == "__main__":
-    asyncio.run(run_cli())
+    asyncio.run(main())