add main.py

main.py

@@ -1,21 +1,20 @@
-import os, asyncio
+import os
+import asyncio
 from dotenv import load_dotenv
-from langchain_openai import ChatOpenAI
-from langchain_core.messages import HumanMessage
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_chroma import Chroma
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_core.documents import Document
+from langchain_tavily import TavilySearchResults
 from langchain.tools import tool
 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
+from langchain_core.messages import HumanMessage
 
-# Load env vars
+# Load environment variables
 load_dotenv()
 
-# ---------- LLM ----------
+# ---------- LLM and Embeddings ----------
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
     base_url="https://openrouter.ai/api/v1",
@@ -23,43 +22,60 @@ 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),
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
 )
 
-# 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()
+# ---------- Vector Store ----------
+CHROMA_DIR = "./chroma_db"
+vector_store = Chroma(collection_name="knowledge", embedding_function=embeddings, persist_directory=CHROMA_DIR)
+
+# ---------- Document Loader ----------
+
+def load_documents(directory: str):
+    """Read .txt/.md files, split into chunks, and add to Chroma collection."""
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    docs = []
+    for root, _, files in os.walk(directory):
+        for file in files:
+            if file.lower().endswith(('.txt', '.md')):
+                path = os.path.join(root, file)
+                with open(path, 'r', encoding='utf-8') as f:
+                    text = f.read()
+                chunks = splitter.split_text(text)
+                docs.extend([Document(page_content=c, metadata={"source": path}) for c in chunks])
+    if docs:
+        vector_store.add_documents(docs)
+        vector_store.persist()
+
+# Load documents once at startup
+if not os.path.exists(CHROMA_DIR) or not os.listdir(CHROMA_DIR):
+    load_documents("./documents")
+
+# ---------- Tavily Search ----------
+TAVILY_API_KEY = os.getenv("TAVILY_API_KEY")
+if not TAVILY_API_KEY:
+    raise ValueError("TAVILY_API_KEY not set in .env")
 
 # ---------- 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)
+    """Semantic search in the local Chroma knowledge base."""
+    docs = vector_store.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:
+    """Web search using Tavily."""
+    results = TavilySearchResults(api_key=TAVILY_API_KEY, max_results=3)
+    search_results = results.run(query)
+    if not search_results:
         return "No web results found."
-    return "\n---\n".join([f"{r['title']}\n{r['content']}" for r in results])
+    return "\n---\n".join([f"{r['title']}\n{r['content']}" for r in search_results])
 
 # ---------- Backend ----------
 backend = CompositeBackend([
@@ -72,13 +88,21 @@ 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 your answer.",
+    system_prompt=(
+        "You are a RAG agent with a local knowledge base and web search capability. "
+        "When a user asks a question, decide whether the answer can be found in the local "
+        "knowledge base or requires up‑to‑date information from the web. Use the tool "
+        "search_local_kb for local queries and web_search for web queries. "
+        "Always indicate the source of the information in your final answer: "
+        "(chromadb) or (tavily)."
+    ),
 )
 
+# ---------- CLI ----------
 async def main():
-    print("Welcome to the RAG agent. Type 'exit' to quit.")
+    print("RAG Agent ready. Type 'exit' to quit.")
     while True:
-        user_input = input("\nQuery: ")
+        user_input = input("\nЗапрос: ")
         if user_input.lower() in {"exit", "quit"}:
             print("Goodbye!")
             break
@@ -86,9 +110,9 @@ async def main():
             {"messages": [HumanMessage(content=user_input)]},
             {"configurable": {"thread_id": "session-1"}},
         )
-        # The agent returns a list of messages; last is the assistant reply
+        # The agent returns a list of messages; the last is the assistant reply
         reply = result["messages"][-1].content
-        print("\nAnswer:\n", reply)
+        print(f"\n{reply}")
 
 if __name__ == "__main__":
     asyncio.run(main())