0.2.3

What's Changed

• Version issues with Fine tuning Embeddings: #72 @taha-aiplanet
• Update the deprecated version for ServiceContext: #73 @adithya-aiplanet

Full Changelog: 0.2.2...0.2.3

0.2.2

What's Changed

• Memory integration: @adithya-aiplanet #60
• Python 3.12 support: @lucifertrj
• Langchain RAG Evaluate using BeyondLLM: cookbook @shivaya-aiplanet #68

New Contributors

• Ollama server URL configurable from user: @jaywyawhare #63
• Add: WeaviateDB Support with example update: @Jai0401 #61 & #65

Full Changelog: 0.2.1.1...0.2.2

0.2.1.1

What's Changed

• Anthropic Sonnet Integration: @tarun-aiplanet #59
• Bug fix with Web Base loaders: @adithya-aiplanet #58

0.2.1

What's Changed

• Observability support to only GPT model: @taha-aiplanet #47
• GPT-4-o support: @adithya-aiplanet #51
• Groq LLM model support for low latency inference: @lucifertrj #54
• Streamlit application for Ingesting and Inferencing BeyondLLM using VectorDB @arya-aiplanet #48
• Cookbook for Language translation using GPT-4-o: @shivaya-aiplanet #52

0.2.0

What's Changed

• VectorDB Support: @adithya-aiplanet added ChromaDB integration to auto_retriever #38
• MultiModal Image Support: @jaintarunAI added the new LLM support for Multimodal that uses Gemini Pro vision #40
• Fine Tune Embeddings: @taha-aiplanet added Fine tune embeddings for RAG as part of Advanced RAG pipeline #39
• Cookbooks: Reference to run BeyondLLM code snippets #36

Contributors

• @lucifertrj and @arya-aiplanet : Added Cookbook support
• @jaintarunAI : Multimodal support
• @adithya-aiplanet : Chroma VectorDB integration
• @taha-aiplanet : Fine Tune Embeddings - Advanced RAG

0.1.0

• Includes source for loading and chunking
• Auto-Retriever: Gives flexibility to pick retriever and embeddings
• Gemini is Default Embeddings and LLM
• 4 Evaluation metrics to evaluate AI response from RAG pipeline
• 2 evaluation metrics for embeddings

New Contributors

• @jaintarunAI
• @adithya-aiplanet
• @taha-aiplanet

Full Changelog: aiplanethub/genai-stack@0.2.5...0.2.6