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

main.py

@@ -1,138 +1,103 @@
 import os
 import asyncio
 from pathlib import Path
-
 from dotenv import load_dotenv
-from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+
+# LangChain imports
+from langchain_ollama import ChatOllama, OllamaEmbeddings
 from langchain_core.documents import Document
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_qdrant import QdrantVectorStore
+from langchain.agents import create_agent
 from langchain.tools import tool
-from deepagents import create_deep_agent
+from langchain_core.messages import HumanMessage
-from deepagents.backends import CompositeBackend, LocalShellBackend, FilesystemBackend
 
-# Load environment variables (OPENAI_API_KEY)
+# Load environment variables (e.g., Ollama host)
 load_dotenv()
 
-# ---------------------------------------------------------------------------
+# LLM and embeddings configuration
-# LLM and embeddings configuration (OpenRouter)
+llm = ChatOllama(model="llama3")
-# ---------------------------------------------------------------------------
+embeddings = OllamaEmbeddings(model="nomic-embed-text")
-llm = ChatOpenAI(
-    model="openai/gpt-oss-20b:free",
-    base_url="https://openrouter.ai/api/v1",
-    api_key=os.getenv("OPENAI_API_KEY"),
-    temperature=0.0,
-)
 
-embeddings = OpenAIEmbeddings(
+# Qdrant client and vector store initialization
-    model="text-embedding-3-small",
-    base_url="https://openrouter.ai/api/v1",
-    api_key=os.getenv("OPENAI_API_KEY"),
-)
-
-# ---------------------------------------------------------------------------
-# Qdrant vector store setup
-# ---------------------------------------------------------------------------
 from qdrant_client import QdrantClient
 
-qdrant_client = QdrantClient(url="http://localhost:6333")  # Qdrant must be running locally
+qdrant_client = QdrantClient(host="localhost", port=6333)
 vector_store = QdrantVectorStore(
-    embedding_function=embeddings,
     client=qdrant_client,
     collection_name="knowledge",
+    embeddings=embeddings,
 )
 
-# ---------------------------------------------------------------------------
 # Text splitter for chunking documents
-# ---------------------------------------------------------------------------
+splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
 
-# ---------------------------------------------------------------------------
+# Tool: Search knowledge base
-# Tools for the agent
-# ---------------------------------------------------------------------------
 @tool
-async def search_knowledge_base(query: str, max_results: int = 5) -> str:
+def search_knowledge_base(query: str, max_results: int = 3) -> str:
-    """Perform a semantic search in the knowledge base."""
+    """Search the knowledge base for relevant information."""
     docs = vector_store.similarity_search(query, k=max_results)
     if not docs:
         return "No relevant documents found."
-    return "\n\n".join([f"Title: {doc.metadata.get('title', 'N/A')}\n{doc.page_content}" for doc in docs])
+    return "\n\n---\n\n".join(f"<{doc.metadata.get('title', 'Untitled')}>
+{doc.page_content}" for doc in docs)
 
+# Tool: Add document to knowledge base
 @tool
-async def add_to_knowledge_base(content: str, title: str = "Unnamed Document") -> str:
+def add_to_knowledge_base(content: str, title: str = "Document") -> str:
-    """Add a document to the knowledge base after chunking."""
+    """Add content to the knowledge base."""
-    chunks = text_splitter.split_text(content)
+    # Split content into chunks
-    docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
+    chunks = splitter.split_text(content)
-    vector_store.add_documents(docs)
+    documents = [Document(page_content=chunk, metadata={"title": title, "chunk_index": idx})
-    return f"Document '{title}' added with {len(chunks)} chunks."
+                 for idx, chunk in enumerate(chunks)]
+    vector_store.add_documents(documents)
+    return f"Added {len(chunks)} chunks from '{title}'."
 
-# ---------------------------------------------------------------------------
+# Agent creation
-# Backend configuration for DeepAgents
+agent = create_agent(
-# ---------------------------------------------------------------------------
+    llm=llm,
-backend = CompositeBackend([
-    LocalShellBackend(workspace_dir="./workspace"),
-    FilesystemBackend(),
-])
-
-# ---------------------------------------------------------------------------
-# DeepAgent definition
-# ---------------------------------------------------------------------------
-agent = create_deep_agent(
-    model=llm,
     tools=[search_knowledge_base, add_to_knowledge_base],
-    backend=backend,
+    system_prompt="You are an AI assistant with access to a knowledge base. Use the provided tools to search and add information."
-    system_prompt="You are a helpful assistant with access to a knowledge base. Use the provided tools to search and add documents. Respond concisely.",
 )
 
-# ---------------------------------------------------------------------------
+# Helper to invoke agent asynchronously
-# Helper function to load all .txt files from a directory into the vector store
+async def invoke_agent(user_input: str) -> str:
-# ---------------------------------------------------------------------------
+    result = await agent.ainvoke(
-async def load_documents_from_directory(directory: str):
+        {"messages": [HumanMessage(content=user_input)]},
-    dir_path = Path(directory)
+        {"configurable": {"thread_id": "session-1"}},
-    for txt_file in dir_path.rglob("*.txt"):
+    )
-        content = txt_file.read_text(encoding="utf-8")
+    # The last message is the agent's reply
-        title = txt_file.stem
+    return result["messages"][-1].content
-        await add_to_knowledge_base(content, title)
-    print(f"Loaded {len(list(dir_path.rglob('*.txt')))} documents from {directory}.")
 
-# ---------------------------------------------------------------------------
+# CLI loop
-# Interactive CLI client
+async def main():
-# ---------------------------------------------------------------------------
+    print("Welcome to the RAG agent CLI. Commands: /add <file_path> | /search <query> | /quit")
-async def interactive_loop():
-    print("Welcome to the RAG Agent CLI. Commands: /add title content | /search query | /quit")
     while True:
-        user_input = input("> ")
+        user_input = input(">>> ")
+        if not user_input:
+            continue
         if user_input.lower() == "/quit":
             print("Goodbye!")
             break
-        if user_input.startswith("/add "):
+        if user_input.lower().startswith("/add "):
-            try:
+            path = user_input[5:].strip()
-                _, rest = user_input.split("/add ", 1)
+            if Path(path).is_file():
-                title, content = rest.split(" ", 1)
+                content = Path(path).read_text(encoding="utf-8")
-            except ValueError:
+                title = Path(path).stem
-                print("Usage: /add title content")
+                # Directly invoke tool via agent
+                response = await invoke_agent(f"Add document: {title}\n{content}")
+            else:
+                print("File not found.")
                 continue
-            human_msg = f"Please add a document titled '{title}' with content: {content}"
+        elif user_input.lower().startswith("/search "):
-        elif user_input.startswith("/search "):
+            query = user_input[8:].strip()
-            query = user_input[len("/search "):]
+            response = await invoke_agent(f"Search for: {query}")
-            human_msg = f"Please search for: {query}"
         else:
             print("Unknown command. Use /add, /search, or /quit.")
             continue
-
+        print("\n--- Agent Response ---\n")
-        result = await agent.ainvoke(
+        print(response)
-            {"messages": [HumanMessage(content=human_msg)]},
+        print("\n-----------------------\n")
-            {"configurable": {"thread_id": "session-1"}},
-        )
-        print(result["messages"][-1].content)
-
-# ---------------------------------------------------------------------------
-# Main entry point
-# ---------------------------------------------------------------------------
-async def main():
-    # Optionally load documents from a directory on startup
-    # await load_documents_from_directory("./data")
-    await interactive_loop()
 
 if __name__ == "__main__":
     asyncio.run(main())