After a short summer break and LangChain's newsletter debut, we're back with a twist! From now on, we're switching to monthly editions and broadening our scope to cover even more cool projects related to LangChain and similar frameworks. Thanks for sticking around, and let's jump into this month's highlights!
Projects
Two big topics in August: Llama2 and fine-tuning.
Meta also introduced Code Llama, a state-of-the-art Large Language Model built on top of Llama 2, available in three specialized models for generating and understanding code and natural language
AutoChain: A lightweight framework for quickly building and evaluating conversational agents using LLMs, facilitating user experiments and customization.
Codeinterpreter-api: A LangChain implementation of the ChatGPT Code Interpreter.
LangSmith-Cookbook: provides tutorials for the LangSmith platform.
Lagent: A lightweight framework for building LLM-based agents.
Marvin: Another lightweight AI engineering framework for building natural language interfaces that are reliable, scalable, and easy to trust.
Monitoring
Mona is an AI monitoring platform that provides valuable insights into ML models and intelligent automation by detecting and resolving issues rapidly while reducing alert fatigue by notifying only specific root causes.
Graphsignal is an AI-native observability platform that offers comprehensive monitoring, debugging, and collaborative tools for AI agents and LLM-powered applications
Langsmith from LangChain, a developer platform for LLM applications to test, monitor, and debug your applications
Videos
Discover the capabilities of Llama2 as a conversational agent in LangChain.
Learn how to bring your personality and tone to LLM apps in the Fine-tuning in Your Voice Webinar.
Articles
LangChain's observability makes it easy to fine-tune LLMs in your unique style by converting messaging platform data here
Enhance your performance and profits using OpenAI's 3.5 Turbo fine-tuning with LangSmith here
Fine-tuning GPT-3.5-Turbo for Natural Language to SQL here
That’s all for this week!
Thank you for being a part of this continuously evolving journey with LangChain! Your passion and backing truly illuminate our community. If this issue struck a chord with you, please share it with others. Together, we only get stronger!
If you believe something was overlooked or have a project in mind, please feel free to connect with us on our GitHub repository or at awesomelangchain[at]kyrolabs.com. We are eager to hear your thoughts.
Stay incredible, and see you in the next update!
This newsletter is crafted with love by the Kyrolabs team.
PS: At Kyrolabs, we are looking for individuals who are enthusiastic about AI Agents and LangChain. If you're keen on embarking on this exhilarating adventure with us, send us a note at contact[at]kyrolabs.com, sharing your interest in AI Agents and background.
Please note that we are not affiliated with the products or services mentioned in this update.