add: main.py

main.py

@@ -0,0 +1,111 @@
+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_core.documents import Document
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+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
+load_dotenv()
+
+# ---------- LLM and Embeddings ----------
+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(
+    model="text-embedding-3-small",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+)
+
+# ---------- Vector Store ----------
+CHROMA_DIR = Path("./chroma_db")
+vector_store = Chroma(
+    collection_name="knowledge",
+    embedding_function=embeddings,
+    persist_directory=str(CHROMA_DIR),
+)
+
+# ---------- Tools ----------
+@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 documents found in local KB."
+    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."""
+    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"{i+1}. {res['title']}\n{res['content'][:200]}..." for i, res in enumerate(results))
+
+# ---------- Backend ----------
+backend = CompositeBackend([
+    LocalShellBackend(workspace_dir="./workspace"),
+    FilesystemBackend(),
+])
+
+# ---------- Agent ----------
+agent = create_deep_agent(
+    model=llm,
+    tools=[search_local_kb, web_search],
+    backend=backend,
+    system_prompt=(
+        "You are a helpful assistant. For any user query, decide whether to use the local knowledge base or perform a web search. "
+        "If the query is about recent events, news, or requires up‑to‑date information, use the web_search tool. "
+        "Otherwise, use search_local_kb. "
+        "Always return the source used in the response (either 'chromadb' or 'tavily')."
+    ),
+)
+
+# ---------- Document Loader ----------
+def load_documents(directory: str, vectorstore: Chroma):
+    """Load .txt and .md files from a directory, chunk them, and add to the vector store."""
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    docs = []
+    for file_path in Path(directory).glob("**/*"):
+        if file_path.suffix.lower() in {".txt", ".md"}:
+            text = file_path.read_text(encoding="utf-8")
+            chunks = splitter.split_text(text)
+            docs.extend([Document(page_content=chunk, metadata={"source": str(file_path)}) for chunk in chunks])
+    if docs:
+        vectorstore.add_documents(docs)
+        vectorstore.persist()
+
+# ---------- CLI ----------
+async def main():
+    # Ensure vector store is loaded
+    if not CHROMA_DIR.exists() or not any(CHROMA_DIR.iterdir()):
+        print("Loading documents into ChromaDB…")
+        load_documents("./documents", vector_store)
+    print("RAG agent ready. Type 'exit' to quit.")
+    while True:
+        user_input = input("\nЗапрос: ")
+        if user_input.lower() in {"exit", "quit"}:
+            break
+        result = await agent.ainvoke(
+            {"messages": [{"role": "user", "content": user_input}]},
+            {"configurable": {"thread_id": "session-1"}},
+        )
+        # Extract last message content
+        content = result["messages"][-1].content
+        print(f"\nОтвет:\n{content}")
+
+if __name__ == "__main__":
+    asyncio.run(main())