bosquet  by zmedelis

LLMOps tooling for building AI applications

Created 2 years ago
348 stars

Top 79.8% on SourcePulse

GitHubView on GitHub
Project Summary

Bosquet provides a Clojure-based toolkit for building sophisticated LLM applications, targeting developers who need to manage complex prompt templating, LLM memory, and agentic interactions. It simplifies the creation of AI-powered applications by offering structured ways to handle prompt composition, chaining, and external tool integration.

How It Works

Bosquet leverages Clojure's functional programming paradigm and integrates with existing libraries like Selmer for templating and Pathom for graph processing. This approach allows for declarative definition of LLM interactions, prompt chaining, and agent logic. The use of Clojure's data-oriented nature facilitates easy management of LLM states, memory, and tool definitions, enabling complex workflows to be expressed concisely.

Quick Start & Requirements

  • Install/Run: clojure -M -m bosquet.cli
  • Prerequisites: Clojure (via clojure CLI tool), API keys for LLM services (e.g., OpenAI, Ollama).
  • Setup: Minimal, primarily involves configuring API keys and optionally sample files.
  • Documentation: Full project documentation (WIP)

Highlighted Details

  • Prompt Templating & Chaining: Utilizes Selmer for templating and Pathom for defining complex prompt chains and compositions.
  • Agent & Tool Support: Provides abstractions for defining agents and integrating external APIs/tools, demonstrated with OpenAI and Ollama.
  • LLM Memory: Includes mechanisms for managing LLM memory within conversations.
  • CLI Interface: Offers a command-line interface for quick testing and generation tasks.

Maintenance & Community

The project is maintained by zmedelis. Community links are not explicitly provided in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The project documentation is marked as "Work In Progress" (WIP), suggesting potential incompleteness or ongoing changes. The absence of a specified license may pose compatibility concerns for commercial applications.

Health Check
Last Commit

2 weeks ago

Responsiveness

1 week

Pull Requests (30d)
1
Issues (30d)
0
Star History
4 stars in the last 30 days

Explore Similar Projects

Starred by Andrej Karpathy Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), Magnus Müller Magnus Müller(Cofounder of Browser Use), and
83 more.

langchain by langchain-ai

0.4%
116k
Framework for building LLM-powered applications
Created 2 years ago
Updated 1 day ago
Feedback? Help us improve.