add main.py

main.py

@@ -1,17 +1,16 @@
-import os
-import asyncio
-from pathlib import Path
+import os, asyncio
 from dotenv import load_dotenv
-
 from langchain_openai import ChatOpenAI
 from langchain_core.messages import HumanMessage
 from langchain.tools import tool
-from langchain_text_splitters import RecursiveCharacterTextSplitter
-from langchain_chroma import Chroma
-from langchain_ollama import OllamaEmbeddings
-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_text_splitters import RecursiveCharacterTextSplitter
+from langchain_ollama import OllamaEmbeddings
+from langchain_ollama import Ollama
+from langchain_tavily import TavilySearchResults
+from pathlib import Path
 
 # Load env vars
 load_dotenv()
@@ -24,57 +23,64 @@ llm = ChatOpenAI(
     temperature=0.0,
 )
 
+# ---------- Vectorstore ----------
+persist_dir = Path("./chroma_db")
+persist_dir.mkdir(parents=True, exist_ok=True)
+
+embeddings = OllamaEmbeddings(model="nomic-embed-text")
+vectorstore = Chroma(
+    collection_name="knowledge",
+    embedding_function=embeddings,
+    persist_directory=str(persist_dir),
+)
+
+# Load documents from ./documents
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+for file_path in Path("./documents").glob("**/*.*"):
+    if file_path.suffix.lower() in {".txt", ".md"}:
+        content = file_path.read_text(encoding="utf-8")
+        docs = text_splitter.split_text(content)
+        vectorstore.add_documents([{"page_content": d, "metadata": {"source": str(file_path)}} for d in docs])
+vectorstore.persist()
+
+# ---------- Tools ----------
+@tool
+def search_local_kb(query: str, top_k: int = 3) -> str:
+    """Semantic search in local ChromaDB knowledge base."""
+    docs = vectorstore.similarity_search(query, k=top_k)
+    if not docs:
+        return "No relevant local knowledge found."
+    return "\n---\n".join([f"{d.metadata.get('source', 'unknown')}\n{d.page_content}" for d in docs])
+
+@tool
+def web_search(query: str) -> str:
+    """Web search via 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"{r['title']}\n{r['content']}" for r in results])
+
 # ---------- Backend ----------
 backend = CompositeBackend([
     LocalShellBackend(workspace_dir="./workspace"),
     FilesystemBackend(),
 ])
 
-# ---------- Vector Store ----------
-PERSIST_DIR = Path("./chroma_db")
-PERSIST_DIR.mkdir(exist_ok=True)
-
-embeddings = OllamaEmbeddings(model="nomic-embed-text")
-vectorstore = Chroma(persist_directory=str(PERSIST_DIR), embedding_function=embeddings)
-
-# Load documents from ./documents if not already loaded
-if not vectorstore.get_collection().count():
-    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    docs = []
-    for file in Path("./documents").glob("*.txt"):
-        text = file.read_text(encoding="utf-8")
-        docs.extend(splitter.split_text(text))
-    vectorstore.add_texts(docs)
-
-# ---------- Tools ----------
-@tool
-def search_local_kb(query: str, top_k: int = 3) -> str:
-    """Semantic search in local ChromaDB knowledge base."""
-    retriever = vectorstore.as_retriever(search_kwargs={"k": top_k})
-    docs = retriever.invoke(query)
-    return "\n".join(doc.page_content for doc in docs) if docs else "No local results found."
-
-@tool
-def web_search(query: str) -> str:
-    """Web search via Tavily."""
-    tavily = TavilySearchResults(api_key=os.getenv("TAVILY_API_KEY"))
-    results = tavily.invoke(query)
-    return "\n".join(f"{r['title']}: {r['url']}" for r in results) if results else "No web results found."
-
 # ---------- Agent ----------
 agent = create_deep_agent(
     model=llm,
     tools=[search_local_kb, web_search],
     backend=backend,
-    system_prompt="You are a helpful RAG agent. For questions about local documents use search_local_kb, for up‑to‑date facts use web_search. Always state the source (chromadb or tavily) in the answer.",
+    system_prompt="You are a helpful RAG agent. For questions about local documents use search_local_kb, for up‑to‑date facts use web_search. Always state the source (chromadb or tavily) in your answer.",
 )
 
-# ---------- CLI ----------
 async def main():
-    print("RAG Agent ready. Type 'exit' to quit.")
+    print("Welcome to the RAG agent. Type 'exit' to quit.")
     while True:
-        user_input = input("\nЗапрос: ")
+        user_input = input("\nQuery: ")
         if user_input.lower() in {"exit", "quit"}:
+            print("Goodbye!")
             break
         result = await agent.ainvoke(
             {"messages": [HumanMessage(content=user_input)]},
@@ -82,7 +88,7 @@ async def main():
         )
         # The agent returns a list of messages; last is the assistant reply
         reply = result["messages"][-1].content
-        print(f"\nОтвет: {reply}")
+        print("\nAnswer:\n", reply)
 
 if __name__ == "__main__":
     asyncio.run(main())