add main.py

main.py

@@ -4,12 +4,13 @@ from pathlib import Path
 from langchain_openai import ChatOpenAI
 from langchain_core.messages import HumanMessage
 from langchain.tools import tool
-from langchain_ollama import OllamaEmbeddings
-from langchain_chroma import Chroma
-from langchain_text_splitters import RecursiveCharacterTextSplitter
-from langchain_tavily import TavilySearchResults
 from deepagents import create_deep_agent
 from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+from langchain_chroma import Chroma
+from langchain_ollama import OllamaEmbeddings
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_ollama import OllamaEmbeddings
+from langchain_tavily import TavilySearchResults
 
 # ---------- LLM ----------
 llm = ChatOpenAI(
@@ -27,42 +28,35 @@ backend = CompositeBackend([
 
 # ---------- Vectorstore utilities ----------
 PERSIST_DIR = Path("./chroma_db")
-PERSIST_DIR.mkdir(parents=True, exist_ok=True)
 
-# Create or load Chroma vectorstore
-vectorstore = Chroma(
-    persist_directory=str(PERSIST_DIR),
-    embedding_function=OllamaEmbeddings(model="nomic-embed-text"),
-)
+def create_vectorstore(persist_directory: str = "./chroma_db"):
+    embeddings = OllamaEmbeddings(model="nomic-embed-text")
+    return Chroma(persist_directory=persist_directory, embedding_function=embeddings)
 
-# Load documents from a directory into the vectorstore
 
 def load_documents(directory: str, vectorstore):
-    docs = []
     splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    for file_path in Path(directory).glob("**/*"):
-        if file_path.suffix.lower() in {".txt", ".md"}:
-            text = file_path.read_text(encoding="utf-8")
+    docs = []
+    for file in Path(directory).glob("**/*"):
+        if file.suffix.lower() in {".txt", ".md"}:
+            text = file.read_text(encoding="utf-8")
             docs.extend(splitter.split_text(text))
-    # Convert to LangChain Documents
+    # Convert to Document objects
     from langchain_core.documents import Document
     documents = [Document(page_content=chunk) for chunk in docs]
     vectorstore.add_documents(documents)
     vectorstore.persist()
 
-# Load documents once at startup (if not already loaded)
-if not any(PERSIST_DIR.iterdir()):
-    load_documents("./documents", vectorstore)
-
 # ---------- Tools ----------
 @tool
 def search_local_kb(query: str, top_k: int = 3) -> str:
     """Semantic search in the local ChromaDB knowledge base."""
+    vectorstore = create_vectorstore(PERSIST_DIR)
     retriever = vectorstore.as_retriever(search_kwargs={"k": top_k})
-    docs = retriever.get_relevant_documents(query)
+    docs = retriever.invoke(query)
     if not docs:
-        return "No relevant documents found in local KB."
-    return "\n---\n".join(doc.page_content for doc in docs)
+        return "No relevant local documents found."
+    return "\n---\n".join(doc.page_content for doc in docs) + "\n[Source: chromadb]"
 
 @tool
 def web_search(query: str) -> str:
@@ -71,39 +65,46 @@ def web_search(query: str) -> str:
     results = tavily.run(query)
     if not results:
         return "No web results found."
-    return "\n---\n".join(f"{r['title']}\n{r['url']}\n{r.get('content', '')}" for r in results)
+    snippets = [f"{r['title']}\n{r['content']}" for r in results]
+    return "\n---\n".join(snippets) + "\n[Source: tavily]"
 
 # ---------- Agent ----------
+SYSTEM_PROMPT = (
+    "You are an AI assistant that can answer questions using either a local knowledge base or the web. "
+    "If the question refers to documents in the local folder, use the `search_local_kb` tool. "
+    "If the question is about recent events or requires up‑to‑date information, use the `web_search` tool. "
+    "Always include the source tag (`[Source: chromadb]` or `[Source: tavily]`) in your answer."
+)
+
 agent = create_deep_agent(
     model=llm,
     tools=[search_local_kb, web_search],
     backend=backend,
-    system_prompt=(
-        "You are an AI assistant that answers user questions.\n"
-        "If the question is about information that should be in the local knowledge base,\n"
-        "use the search_local_kb tool.\n"
-        "If the question requires up‑to‑date information from the web,\n"
-        "use the web_search tool.\n"
-        "Always indicate the source of the answer in the format:\n"
-        "[Source: chromadb] or [Source: tavily] before the answer."
-    ),
+    system_prompt=SYSTEM_PROMPT,
 )
 
 # ---------- CLI ----------
-async def main():
-    print("RAG Agent with ChromaDB and Tavily. Type 'exit' to quit.")
+async def chat_loop():
+    print("RAG Agent ready. Type 'exit' to quit.")
     while True:
         user_input = input("\nЗапрос: ")
-        if user_input.lower() in {"exit", "quit"}:
+        if user_input.strip().lower() == "exit":
             print("Goodbye!")
             break
         result = await agent.ainvoke(
             {"messages": [HumanMessage(content=user_input)]},
             {"configurable": {"thread_id": "session-1"}},
         )
-        # The agent returns a list of messages; the last is the assistant reply
+        # The last message is the assistant's reply
         reply = result["messages"][-1].content
-        print(f"\n{reply}")
+        print(reply)
 
+# ---------- Initialization ----------
 if __name__ == "__main__":
-    asyncio.run(main())
+    # Ensure vectorstore exists and load documents if empty
+    vectorstore = create_vectorstore(PERSIST_DIR)
+    if not vectorstore.get_all_documents():
+        print("Loading documents into ChromaDB...")
+        load_documents("./documents", vectorstore)
+        print("Documents loaded.")
+    asyncio.run(chat_loop())