lc-cli

Crates.iolc-cli
lib.rslc-cli
version0.1.0
created_at2025-08-12 08:22:52.130505+00
updated_at2025-08-12 08:22:52.130505+00
descriptionLLM Client - A fast Rust-based LLM CLI tool with provider management and chat sessions
homepagehttps://lc.viwq.dev
repositoryhttps://github.com/your-username/lc
max_upload_size
id1791639
size5,434,288
Rajashekar Chintalapati (rajashekar)

documentation

README

Documentation License Rust

LLM Client (lc)

LLM Client

A fast, Rust-based command-line tool for interacting with Large Language Models.

Quick Start

# Option 1: Install from crates.io (when published)
cargo install lc-cli

# Option 2: Install from source
git clone <repository-url>
cd lc
cargo build --release

# Add a provider
lc providers add openai https://api.openai.com/v1

# Set your API key
lc keys add openai

# Start chatting
lc -m openai:gpt-4 "What is the capital of France?"
or
# set default provider and model
lc config set provider openai
lc config set model gpt-4
# Direct prompt with specific model
lc "What is the capital of France?"

Key Features

  • 🚀 Lightning Fast - ~3ms cold start (50x faster than Python alternatives)
  • 🔧 Universal - Works with any OpenAI-compatible API
  • 🧠 Smart - Built-in vector database and RAG support
  • 🛠️ Tools - Model Context Protocol (MCP) support for extending LLM capabilities
  • 🔍 Web Search - Integrated web search with multiple providers (Brave, Exa, Serper) for enhanced context
  • 👁️ Vision Support - Process and analyze images with vision-capable models
  • � PDF Support - Read and process PDF files with optional dependency
  • 🔐 Secure - Encrypted configuration sync
  • 💬 Intuitive - Simple commands with short aliases
  • 🎨 Flexible Templates - Configure request/response formats for any LLM API
  • ⚡ Shell Completion - Tab completion for commands, providers, models, and more

Shell Completion

lc supports comprehensive tab completion for all major shells (Bash, Zsh, Fish, PowerShell, Elvish) with both static and dynamic completion:

# Generate completion script for your shell
lc completions bash > ~/.local/share/bash-completion/completions/lc
lc completions zsh > ~/.local/share/zsh/site-functions/_lc
lc completions fish > ~/.config/fish/completions/lc.fish

# Dynamic provider completion
lc -p <TAB>                 # Shows all configured providers
lc -p g<TAB>                # Shows providers starting with "g"

# Command completion
lc providers <TAB>          # Shows provider subcommands
lc config set <TAB>         # Shows configuration options

For detailed setup instructions, see Shell Completion Guide.

Documentation

For comprehensive documentation, visit lc.viwq.dev

Quick Links

Supported Providers

Any OpenAI-compatible API can be used with lc. Here are some popular providers: Anthropic, Gemini, and Amazon Bedrock also supported.

Amazon Bedrock Setup

Amazon Bedrock requires a special configuration due to its different endpoints for model listing and chat completions:

# Add Bedrock provider with different endpoints
lc providers add bedrock https://bedrock-runtime.us-east-1.amazonaws.com \
  -m /foundation-models \
  -c "https://bedrock-runtime.us-east-1.amazonaws.com/model/{model_name}/converse"

# Set your AWS Bearer Token
lc keys add bedrock

# List available models
lc providers models bedrock

# Use Bedrock models
lc -m bedrock:amazon.nova-pro-v1:0 "Hello, how are you?"

# Interactive chat with Bedrock
lc chat -m bedrock:amazon.nova-pro-v1:0

Key differences for Bedrock:

  • Models endpoint: Uses https://bedrock.us-east-1.amazonaws.com/foundation-models
  • Chat endpoint: Uses https://bedrock-runtime.us-east-1.amazonaws.com/model/{model_name}/converse
  • Authentication: Requires AWS Bearer Token for Bedrock
  • Model names: Use full Bedrock model identifiers (e.g., amazon.nova-pro-v1:0)

The {model_name} placeholder in the chat URL is automatically replaced with the actual model name when making requests.

Example Usage

# Direct prompt with specific model
lc -m openai:gpt-4 "Explain quantum computing"

# Interactive chat session
lc chat -m anthropic:claude-3.5-sonnet

# Create embeddings
lc embed -m openai:text-embedding-3-small -v knowledge "Important information"

# Search similar content
lc similar -v knowledge "related query"

# RAG-enhanced chat
lc -v knowledge "What do you know about this topic?"

# Use MCP tools for internet access
lc -t fetch "What's the latest news about AI?"

# Multiple MCP tools
lc -t fetch,playwright "Navigate to example.com and analyze its content"

# Web search integration
lc --use-search brave "What are the latest developments in quantum computing?"

# Search with specific query
lc --use-search "brave:quantum computing 2024" "Summarize the findings"

# Generate images from text prompts
lc image "A futuristic city with flying cars" -m dall-e-3 -s 1024x1024
lc img "Abstract art with vibrant colors" -c 2 -o ./generated_images

Web Search Integration

lc supports web search integration to enhance prompts with real-time information:

# Configure Brave Search
lc search provider add brave https://api.search.brave.com/res/v1/web/search -t brave
lc search provider set brave X-Subscription-Token YOUR_API_KEY

# Configure Exa (AI-powered search)
lc search provider add exa https://api.exa.ai -t exa
lc search provider set exa x-api-key YOUR_API_KEY

# Configure Serper (Google Search API)
lc search provider add serper https://google.serper.dev -t serper
lc search provider set serper X-API-KEY YOUR_API_KEY

# Set default search provider
lc config set search brave

# Direct search
lc search query brave "rust programming language" -f json
lc search query exa "machine learning best practices" -n 10
lc search query serper "latest AI developments" -f md

# Use search results as context
lc --use-search brave "What are the latest AI breakthroughs?"
lc --use-search exa "Explain transformer architecture"
lc --use-search serper "What are the current trends in quantum computing?"

# Search with custom query
lc --use-search "brave:specific search terms" "Analyze these results"
lc --use-search "exa:neural networks 2024" "Summarize recent advances"
lc --use-search "serper:GPT-4 alternatives 2024" "Compare the latest language models"

Image Generation

lc supports text-to-image generation using compatible providers:

# Basic image generation
lc image "A beautiful sunset over mountains"

# Generate with specific model and size
lc image "A futuristic robot" -m dall-e-3 -s 1024x1024

# Generate multiple images
lc image "Abstract geometric patterns" -c 4

# Save to specific directory
lc image "A cozy coffee shop" -o ./my_images

# Use short alias
lc img "A magical forest" -m dall-e-2 -s 512x512

# Generate with specific provider
lc image "Modern architecture" -p openai -m dall-e-3

# Debug mode to see API requests
lc image "Space exploration" --debug

Supported Parameters:

  • -m, --model: Image generation model (e.g., dall-e-2, dall-e-3)
  • -p, --provider: Provider to use (openai, etc.)
  • -s, --size: Image size (256x256, 512x512, 1024x1024, 1792x1024, 1024x1792)
  • -c, --count: Number of images to generate (1-10, default: 1)
  • -o, --output: Output directory for saved images (default: current directory)
  • --debug: Enable debug mode to see API requests

Note: Image generation is currently supported by OpenAI-compatible providers. Generated images are automatically saved with timestamps and descriptive filenames.

Vision/Image Support

lc supports image inputs for vision-capable models across multiple providers:

# Single image analysis
lc -m gpt-4-vision-preview -i photo.jpg "What's in this image?"

# Multiple images
lc -m claude-3-opus-20240229 -i before.jpg -i after.jpg "Compare these images"

# Image from URL
lc -m gemini-pro-vision -i https://example.com/image.jpg "Describe this image"

# Interactive chat with images
lc chat -m gpt-4-vision-preview -i screenshot.png

# Find vision-capable models
lc models --vision

# Combine with other features
lc -m gpt-4-vision-preview -i diagram.png -a notes.txt "Explain this diagram with the context from my notes"

Supported formats: JPG, PNG, GIF, WebP (max 20MB per image)

Model Context Protocol (MCP)

lc supports MCP servers to extend LLM capabilities with external tools:

# Add an MCP server
lc mcp add fetch "uvx mcp-server-fetch" --type stdio

# List available functions
lc mcp functions fetch

# Use tools in prompts
lc -t fetch "Get the current weather in Tokyo"

# Interactive chat with tools
lc chat -m gpt-4 -t fetch

Platform Support for MCP Daemon:

  • Unix systems (Linux, macOS, WSL2): Full MCP daemon support with persistent connections via Unix sockets (enabled by default with the unix-sockets feature)
  • Windows: MCP daemon functionality is not available due to lack of Unix socket support. Direct MCP connections without the daemon work on all platforms.
  • WSL2: Full Unix compatibility including MCP daemon support (works exactly like Linux)

To build without Unix socket support:

cargo build --release --no-default-features --features pdf

Learn more about MCP in our documentation.

File Attachments and PDF Support

lc can process and analyze various file types, including PDFs:

# Attach text files to your prompt
lc -a document.txt "Summarize this document"

# Process PDF files (requires PDF feature)
lc -a report.pdf "What are the key findings in this report?"

# Multiple file attachments
lc -a file1.txt -a data.pdf -a config.json "Analyze these files"

# Combine with other features
lc -a research.pdf -v knowledge "Compare this with existing knowledge"

# Combine images with text attachments
lc -m gpt-4-vision-preview -i chart.png -a data.csv "Analyze this chart against the CSV data"

Note: PDF support requires the pdf feature (enabled by default). To build without PDF support:

cargo build --release --no-default-features

To explicitly enable PDF support:

cargo build --release --features pdf

Template System

lc supports configurable request/response templates, allowing you to work with any LLM API format without code changes:

# Fix GPT-5's max_completion_tokens and temperature requirement
[chat_templates."gpt-5.*"]
request = """
{
  "model": "{{ model }}",
  "messages": {{ messages | json }}{% if max_tokens %},
  "max_completion_tokens": {{ max_tokens }}{% endif %},
  "temperature": 1{% if tools %},
  "tools": {{ tools | json }}{% endif %}{% if stream %},
  "stream": {{ stream }}{% endif %}
}
"""

See Template System Documentation and config_samples/templates_sample.toml for more examples.

Features

lc supports several optional features that can be enabled or disabled during compilation:

Default Features

  • pdf: Enables PDF file processing and analysis
  • unix-sockets: Enables Unix domain socket support for MCP daemon (Unix systems only)

Build Options

# Build with all default features
cargo build --release

# Build with minimal features (no PDF, no Unix sockets)
cargo build --release --no-default-features

# Build with only PDF support (no Unix sockets)
cargo build --release --no-default-features --features pdf

# Build with only Unix socket support (no PDF)
cargo build --release --no-default-features --features unix-sockets

# Explicitly enable all features
cargo build --release --features "pdf,unix-sockets"

Note: The unix-sockets feature is only functional on Unix-like systems (Linux, macOS, BSD, WSL2). On Windows native command prompt/PowerShell, this feature has no effect and MCP daemon functionality is not available regardless of the feature flag. WSL2 provides full Unix compatibility.

Feature Windows macOS Linux WSL2
MCP Daemon ❌ ✅ ✅ ✅
Direct MCP ✅ ✅ ✅ ✅

Contributing

Contributions are welcome! Please see our Contributing Guide.

License

MIT License - see LICENSE file for details.

For detailed documentation, examples, and guides, visit lc.viwq.dev

Commit count: 0

cargo fmt