Vector Chat - Rust

A Rust implementation of a Retrieval-Augmented Generation (RAG) workflow: it embeds text with OpenAI, indexes in Qdrant, retrieves relevant context, and generates AI chat responses enriched with that context.

Features

• Text embedding using OpenAI's embedding models
• Vector storage in Qdrant database
• Semantic search for relevant context
• AI-powered chat with context retrieval
• Command-line interface for easy interaction

Prerequisites

• OpenAI API key
• Rust (1.65.0 or later)
• Qdrant

Note: You can run Qdrant using docker, or visit the official website for more information.

docker run -p 6333:6333 qdrant/qdrant

Setup

Create a .env file with your OpenAI API key and Qdrant settings:

# OpenAI API Key
OPENAI_API_KEY=your_openai_api_key_here

# Qdrant settings (using local Qdrant instance by default)
QDRANT_URL=http://localhost:6333
QDRANT_COLLECTION=rustchat
# QDRANT_API_KEY=your_qdrant_api_key_if_needed

# OpenAI models
DEFAULT_CHAT_MODEL=gpt-4o
DEFAULT_EMBEDDING_MODEL=text-embedding-3-small

Usage

Embedding Text

# Embed a file
cargo run embed --file path/to/file.txt

# Embed direct text input
cargo run embed --text "This is some text to embed"

# List available text files
cargo run embed --list-files

Chat with Context

# Chat with context retrieval (default)
cargo run chat

# Chat without context retrieval (using only OpenAI's knowledge)
cargo run chat --no-context

Build the project:

cargo build --release

# Embed a file
./target/release/vector-chat embed --file path/to/file.txt

# Embed direct text input
./target/release/vector-chat embed --text "This is some text to embed"

# List available text files
./target/release/vector-cha embed --list-files

# Chat with context retrieval (default)
./target/release/vector-cha chat

Installation

You can install the binary directly using:

cargo install --path .

This will make the vector-chat command available globally.

License

MIT License