From e8d12abe75e1574bbbac92a5f282bf05e748ca66 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9A=D0=B8=D1=80=D0=B8=D0=BB=D0=BB=20=D0=A0=D0=BE=D0=BC?=
 =?UTF-8?q?=D0=B0=D0=BD=D0=BE=D0=B2?= <kirilinka320@gmail.com>
Date: Thu, 4 Jun 2026 22:56:48 +0000
Subject: [PATCH] Update README.md

---
 README.md | 92 +++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 63 insertions(+), 29 deletions(-)

diff --git a/README.md b/README.md
index f64ac73..98a8071 100644
--- a/README.md
+++ b/README.md
@@ -1,50 +1,84 @@
-# RAG Agent with Qdrant and Ollama
+# RAG‑Agent with Qdrant & Ollama
 
-This repository contains a minimal but fully‑functional example of an AI agent that uses **Qdrant** as a local vector store, **Ollama** for embeddings and a local LLM, and **LangChain** for the agent logic.
+This repository contains a minimal but functional implementation of a **RAG (Retrieval‑Augmented Generation) agent** that:
 
-## Features
+* Stores embeddings in a **Qdrant** vector database.
+* Generates embeddings with **Ollama** (`nomic-embed-text`).
+* Uses **LangChain** (v1+) for the agent, tools and prompt‑engineering.
 
-* **Semantic search** – `search_knowledge_base` tool queries the vector store.
-* **Document ingestion** – `add_to_knowledge_base` tool splits text into chunks and stores them.
-* **Interactive CLI** – simple command line interface for adding documents, searching and chatting with the agent.
-* **Modular design** – vector store, tools and agent logic are separated into distinct modules.
+The agent can:
 
-## Setup
+* Search the knowledge base (`/search`).
+* Add new documents (`/add`).
+* Interact through a simple CLI.
+
+## Installation
 
 ```bash
-# 1. Install Ollama models
+# 1. Pull required Ollama models
 ollama pull llama3
 ollama pull nomic-embed-text
 
 # 2. Install Python dependencies
 pip install -r requirements.txt
 
-# 3. Start Qdrant (Docker recommended)
-#    docker run -p 6333:6333 qdrant/qdrant
+# 3. Run the CLI
+python -m src.cli
+```
+
+> **Note**: Qdrant must be running locally on port 6333. You can start it using Docker:
+>
+> ```bash
+> docker run -p 6333:6333 qdrant/qdrant
+> ```
+
+## Directory structure
+
+```
+workspace/task-6a02e23da6fe2e4ac16acf65/
+├─ src/
+│  ├─ vector_store.py   # Qdrant wrapper
+│  ├─ tools.py          # LangChain tools
+│  ├─ agent.py          # Agent implementation
+│  ├─ loader.py         # Utility for bulk loading
+│  └─ cli.py            # Interactive CLI
+├─ requirements.txt
+└─ README.md
 ```
 
 ## Usage
 
+### Load documents from a folder
+
 ```bash
-python -m workspace.task-6a02e23da6fe2e4ac16acf65.cli
+python -m src.loader /path/to/text/files
 ```
 
-The CLI accepts the following commands:
-
-* `/add <title>` – add a new document. After the title you will be prompted to paste the content; finish with a line containing only `END`.
-* `/search <query>` – perform a semantic search.
-* `/quit` – exit.
-
-Anything else is forwarded to the agent.
-
-## Project structure
+### Start the interactive CLI
 
+```bash
+python -m src.cli
 ```
-workspace/
-├── task-6a02e23da6fe2e4ac16acf65/
-│   ├── agent.py          # Agent and tool definitions
-│   ├── cli.py            # Interactive command line interface
-│   ├── vector_store.py   # Qdrant + Ollama wrapper
-│   ├── requirements.txt
-│   └── README.md
-```
\ No newline at end of file
+
+- `/add` – add a new document.
+- `/search` – perform a semantic search.
+- `/quit` – exit.
+
+Any other input is treated as a user message and processed by the agent.
+
+## How it works
+
+1. **Vector store** – `KnowledgeBase` wraps `QdrantVectorStore`. It splits documents into chunks using `RecursiveCharacterTextSplitter`, embeds them with `OllamaEmbeddings`, and stores the vectors.
+2. **Tools** – Two tools (`search_knowledge_base`, `add_to_knowledge_base`) are exposed to the agent via LangChain's `@tool` decorator.
+3. **Agent** – Built with `create_tool_calling_agent` and `AgentExecutor`. The system prompt encourages the assistant to use the tools.
+4. **CLI** – Provides a simple REPL for adding documents, searching, and chatting with the agent.
+
+## Extending
+
+* Replace the embedding model with any Ollama model.
+* Swap Qdrant for another vector store supported by LangChain.
+* Add more tools (e.g., delete, update) following the same pattern.
+
+---
+
+Happy experimenting!
\ No newline at end of file