feat: solution for 'Агент с RAG-памятью'

README.md

@@ -1,12 +1,14 @@
-# Agent with RAG Memory
+# RAG Agent with LangChain, Qdrant, and Ollama
 
-This project demonstrates a simple RAG (Retrieval-Augmented Generation) agent that uses LangChain tools to perform basic operations via an interactive command line interface (CLI).
+This repository contains a minimal example of a Retrieval-Augmented Generation (RAG) agent built with **LangChain**, **Qdrant**, and **Ollama**. The agent retrieves relevant documents from a local Qdrant vector store and generates answers using an Ollama language model.
 
-## Features
+## Prerequisites
 
-- **Add Numbers** – Add two integers using the `add_numbers` tool.
-- **Search Items** – Search a predefined list of strings for a query using the `search_item` tool.
-- **Interactive CLI** – Use `/add`, `/search`, and `/quit` commands to interact with the agent.
+- **Python 3.10+**  
+- **Qdrant** server running locally (default port `6333`).  
+  - Create a collection named `rag_collection` and populate it with embeddings.  
+- **Ollama** server running locally (default port `11434`).  
+  - Ensure the model `llama3.1` (or any other supported model) is available.
 
 ## Installation
 
@@ -17,7 +19,7 @@ cd agent-s-rag-pamyatyu
 
 # Create a virtual environment (optional but recommended)
 python -m venv .venv
-source .venv/bin/activate  # On Windows use `.venv\\Scripts\\activate`
+source .venv/bin/activate  # On Windows: .venv\\Scripts\\activate
 
 # Install dependencies
 pip install -r requirements.txt
@@ -25,72 +27,34 @@ pip install -r requirements.txt
 
 ## Usage
 
-Run the CLI:
-
 ```bash
 python -m src.main
 ```
 
-You will see a prompt:
-
-```
-Welcome to the RAG Agent CLI!
-Available commands:
-  /add <int> <int>   - Add two numbers.
-  /search <query>   - Search items in memory.
-  /quit             - Exit the program.
-```
-
-### Commands
-
-- **/add**  
-  Add two integers.
-
-  ```text
-  >> /add 5 7
-  Result: 12
-  ```
-
-- **/search**  
-  Search the internal memory for a query string.
-
-  ```text
-  >> /search python
-  Matches found:
-    1. Python programming
-  ```
-
-- **/quit**  
-  Exit the program.
-
-  ```text
-  >> /quit
-  Goodbye!
-  ```
+You will be prompted to enter a question. The agent will retrieve relevant documents from Qdrant and generate an answer using Ollama. Type `exit` or `quit` to terminate the program.
 
 ## Project Structure
 
 ```
 agent-s-rag-pamyatyu/
-├── src/
-│   ├── __init__.py
-│   ├── cli.py
-│   ├── main.py
-│   └── tools.py
-├── README.md
 ├── requirements.txt
-└── pyproject.toml
+├── src/
+│   └── main.py
+└── README.md
 ```
 
-## Dependencies
+- `requirements.txt` – lists all Python dependencies, including `langchain-qdrant` and `langchain-ollama`.
+- `src/main.py` – contains the RAG agent implementation.
+- `README.md` – this documentation file.
 
-- `langchain` – The core library for building language model agents.
-- `python-dotenv` – (Optional) For loading environment variables if needed.
+## Troubleshooting
+
+- **Missing dependencies**: Ensure you ran `pip install -r requirements.txt`.  
+- **Qdrant connection errors**: Verify Qdrant is running and the collection name matches `rag_collection`.  
+- **Ollama connection errors**: Verify Ollama is running and the model name is correct.
 
 ## License
 
-MIT License
+This project is provided as-is for educational purposes. Feel free to modify and extend it.
 
 ---
-
-Feel free to extend the tools or the CLI to suit your needs!

requirements.txt

@@ -1,2 +1,5 @@
-langchain>=0.0.0
-python-dotenv>=0.21.0
+langchain>=0.2.0
+langchain-qdrant>=0.1.0
+langchain-ollama>=0.1.0
+qdrant-client>=1.0.0
+pydantic>=2.0.0

src/main.py

@@ -1,7 +1,111 @@
-from .cli import run_cli
+"""
+Simple RAG agent using LangChain, Qdrant, and Ollama.
+
+This script demonstrates how to set up a retrieval-augmented generation (RAG) pipeline
+with a local Qdrant vector store and an Ollama LLM. It can be run directly:
+
+    python -m src.main
+
+The script will prompt the user for a question and return an answer based on the
+documents stored in Qdrant.
+
+Prerequisites:
+- Qdrant server running locally (default port 6333).
+- Ollama server running locally (default port 11434).
+- A Qdrant collection named "rag_collection" populated with embeddings.
+"""
+
+import os
+import sys
+from typing import Optional
+
+try:
+    from langchain_ollama import OllamaLLM
+    from langchain_qdrant import QdrantStore
+    from langchain.chains import RetrievalQA
+    from langchain.memory import ConversationBufferMemory
+except ImportError as e:
+    print("Required packages are missing. Please run 'pip install -r requirements.txt'.")
+    sys.exit(1)
+
+
+def get_llm() -> OllamaLLM:
+    """
+    Create an Ollama LLM instance.
+    """
+    # Ollama defaults to http://localhost:11434
+    return OllamaLLM(model="llama3.1")
+
+
+def get_vector_store() -> QdrantStore:
+    """
+    Connect to the local Qdrant instance and load the collection.
+    """
+    # Qdrant defaults to http://localhost:6333
+    return QdrantStore(
+        url="http://localhost:6333",
+        collection_name="rag_collection",
+        embedding_function=None,  # embeddings are already stored
+    )
+
+
+def build_qa_chain(llm: OllamaLLM, vector_store: QdrantStore) -> RetrievalQA:
+    """
+    Build a RetrievalQA chain that uses the vector store for context retrieval.
+    """
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+
+    return RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=vector_store.as_retriever(search_kwargs={"k": 4}),
+        memory=memory,
+        return_source_documents=True,
+    )
+
 
 def main() -> None:
-    run_cli()
+    """
+    Main entry point: prompt user for a question and print the answer.
+    """
+    print("Initializing RAG agent...")
+    try:
+        llm = get_llm()
+        vector_store = get_vector_store()
+        qa_chain = build_qa_chain(llm, vector_store)
+    except Exception as exc:
+        print(f"Failed to initialize components: {exc}")
+        sys.exit(1)
+
+    print("RAG agent ready. Type your question (or 'exit' to quit).")
+    while True:
+        try:
+            user_input = input("\n> ").strip()
+        except (EOFError, KeyboardInterrupt):
+            print("\nExiting.")
+            break
+
+        if user_input.lower() in {"exit", "quit"}:
+            print("Goodbye!")
+            break
+
+        if not user_input:
+            print("Please enter a non-empty question.")
+            continue
+
+        try:
+            result = qa_chain({"question": user_input})
+            answer = result.get("answer", "No answer returned.")
+            sources = result.get("source_documents", [])
+            print("\nAnswer:")
+            print(answer)
+            if sources:
+                print("\nSources:")
+                for doc in sources:
+                    print(f"- {doc.metadata.get('source', 'unknown')}")
+        except Exception as exc:
+            print(f"Error during query: {exc}")
+
 
 if __name__ == "__main__":
     main()