Here are 9 projects to take your app to the next level in 2023.

[Lunary](https://github.com/lunary-ai/lunary) (sponsored)

[Guidance](https://github.com/guidance-ai/guidance)

[LiteLLM](https://github.com/BerriAI/litellm)

[LangChain](https://github.com/langchain-ai/langchain)

[DeepEval](https://github.com/confident-ai/deepeval)

[pgVector](https://github.com/pgvector/pgvector)

[promptfoo](https://github.com/promptfoo/promptfoo)

[Model Fusion](https://github.com/lgrammel/modelfusion)

9 Open Source tools to take your AI app to the next level

In the era of AI-driven applications, the ability to efficiently handle and search through vector data is crucial.

🌌 [Lunary.ai](https://github.com/lunary-ai/lunary)

🧲 [PGVector](https://github.com/pgvector/pgvector)

🌐 [Weaviate](https://github.com/weaviate/weaviate)

🎨 [ChromaDB](https://github.com/chroma-core/chroma)

🔍 [Milvus](https://github.com/milvus-io/milvus)

🧭 [Qdrant](https://github.com/qdrant/qdrant)

🔎 [ElasticSearch](https://github.com/elastic/elasticsearch)

6 Open-Source Vector Databases to Power Your AI App

Here are 7 open-source tools that you can add to your development workflow to be faster and more productive. These tools go from simple code completion, to full fledged app builders.

🤖 [continue](https://github.com/continuedev/continue)

🏎️ [gpt-pilot](https://github.com/Pythagora-io/gpt-pilot)

📝 [auto-commit](https://github.com/m1guelpf/auto-commit)

🏗️ [ChatDev](https://github.com/OpenBMB/ChatDev)

🧑‍🚀 [TabbyML](https://github.com/TabbyML/tabby)

🛜 [localpilot](https://github.com/danielgross/localpilot)

📈 [lunary](https://github.com/lunary-ai/lunary)

🍥 [swirl](https://github.com/swirlai/swirl-search)

7 Open Source AI projects to code faster in 2023

Discover 5 alternatives to LangSmith to observe, evaluate and improve your LangChain and LLM apps.

LangSmith alternatives: 5 tools to capture LLM data

Datadog is a popular monitoring tool for infrastructure and applications. Let's see why and explore alternatives.

Datadog LLM Observability: Examples, Demo and Pricing

Prompt Templates, Chat Tracking in Python and faster dashboard.

December 2023 Update

Claude v3, evaluations and stability improvements.

February 2024 Update

Radars, evaluations out of private alpha & major app overhaul.

January 2024 Update

A guide on how we can efficiently format the user prompts with the HumanMessage class and use it into our LLM Models for improved context.

Initialize message list with system message

Trigger the chat model to generate the response

Inform the user that the conversation has ended

Observe your AI Application performance with Lunary 

Understanding the LangChain HumanMessage class for LLMs

Comparing how state of the art LLMs handle generating SVGs.

Draw me an SVG

March 2024 Update

Analytics v2, Tool calling data in prompts, and much more.

April+May 2024 Update

Prompt Playground, more supported models & a lot more.

🔍 Prompt Playground in public beta (give us feedback!)

🗃️ Public API & AI Evaluations in beta access

🐛 Support for OpenAI streaming queries in Python & JS 

🐥 LangChain support of AWS Bedrock, Google Palm and Anthropic

November 2023 Update

Search & filter, exports, chat replays and lots of fixes.

October 2023 Update

Discover the key differences between OpenAI's o1 models and GPT-4o, and when each model is most effective.

Q: What are the limitations of o1 models?

Q: What measures has OpenAI taken to ensure o1's safety?

When does it make sense to use o1 vs GPT-4o?

Generating some random data for demonstration

Let's create a dataset with 100 samples, each with 4 features

And some random target values (since this is just a demonstration, the targets don't have to make sense)

After training, you can use model.predict() to make predictions on new data

Understanding LLM Parameters

We're changing our name to Lunary.ai. Here's why.

LLMonitor is now Lunary.ai

Comparing Claude 3, GPT-4, Gemini 1.5, and Mistral Large on various tasks.