CAMEL Release Notes [Sprint 4]

Hey everyone! We're thrilled to share some exciting updates this week, including new integrations, enhanced features, and important improvements. From adding support for various AI models to integrating new toolkits and libraries, we've made significant strides in expanding our framework's capabilities. Check out the highlights below!


๐Ÿ”ฎ Modality updates:

  • ๐Ÿ”ฎ Video Description Feature: We've just integrated a video description feature into the ๐Ÿซ CAMEL framework! See the example below where an agent can get Figma's latest demo about Figma Slides and generate a social media post highlighting the main features and moments mentioned. Just use the prompt: Create a compelling social media post based on the key highlights of this video. Thanks to raywhoelse for working on this. Explore more here.
  • ๐Ÿ”ฎ Integration of VLM Embedding Model: We've integrated the VLM Embedding Model into the CAMEL framework, enhancing our ability to generate rich and detailed embeddings from both text and image inputs. Thanks to FUYICC for making this happen. Explore more here.

๐Ÿ›  Tool updates:

  • ๐Ÿ›  Add Zhipu AI Models: Weโ€™ve just integrated Zhipu AIโ€™s models into the CAMEL framework, enabling developers to leverage multilingual models like glm-3-turbo, glm-4, and glm-4v. Big thanks to our contributor fengju0213 for this integration! Explore more here.
  • ๐Ÿ›  GithubToolkit Integration: We've integrated the GithubToolkit into the CAMEL framework! Now, you can automate the retrieval and summarization of pull requests, making project tracking and reporting seamless. Perfect for creating weekly summaries and enhancing collaboration. Kudos to our contributor rsrbk for this valuable addition. Explore more here.
  • ๐Ÿ›  Add Support for LiteLLM Library: Weโ€™ve integrated the LiteLLM library into the CAMEL framework! LiteLLM provides a unified interface to interact with over 100 large language model providers, allowing our agents to leverage a diverse array of LLMs. Thanks to ZackYule for this incredible work! Explore more here.
  • ๐Ÿ›  Integrate Ollama Model: We've integrated Ollama into the CAMEL framework! Ollama allows users to run large language models locally. It supports models like Llama 3, Phi 3, Mistral, and Gemma. Big thanks to Wendong-Fan for this addition! Explore more here.

๐Ÿ’ก Others:

  • ๐Ÿ’ก Support API Key for OpenAPI Functions: We've enhanced the API functionality to support API keys, improving security and access control. Thanks to yiyiyi0817 for this, explore more here.
  • ๐Ÿ’ก Contribution Guideline Update: Weโ€™ve updated our contribution guidelines to make it easier for new contributors to get started. Thanks to Wendong-Fan for this, explore more here.
  • ๐Ÿ’ก Type Hint and Docstring Enhancement: We've made small enhancements to type hints and docstrings, improving code clarity and maintainability. Thanks to Wendong-Fan for this, explore more here.

๐Ÿซ Thanks from everyone at CAMEL-AI

Hello there, passionate AI enthusiasts! ๐ŸŒŸ We are ๐Ÿซ, a global coalition of students, researchers, and engineers dedicated to advancing the frontier of AI and fostering a harmonious relationship between agents and humans.

๐Ÿ“˜ Our Mission: To harness the potential of AI agents in crafting a brighter and more inclusive future for all. Every contribution we receive helps push the boundaries of whatโ€™s possible in the AI realm.

๐Ÿ™Œ Join Us: If you believe in a world where AI and humanity coexist and thrive, then youโ€™re in the right place. Your support can make a significant difference. Letโ€™s build the AI society of tomorrow, together!