Evaluate #RAG with #RAGAs Ragas provides you with the tools/metrics based on the latest research for evaluating LLM-generated text to give you insights about your RAG pipeline. ragas can be integrated with your CI/CD to provide continuous checks to ensure performance. In this evaluation, #GPT4-o is used as an LLM to generate responses out of semantically close context chunks. ✅ Evaluate on Colab - https://lnkd.in/gjrKiY6a 🌟 Checkout other evaluation examples - https://lnkd.in/gwQAAbkb #evaluation #rag #ragas #vectordb
LanceDB
Information Services
San Francisco, California 4,950 followers
Developer-friendly, open source database for multi-modal AI
About us
LanceDB is a developer-friendly, open source database for multimodal AI. From hyper scalable vector search to advanced retrieval for RAG, from streaming training data to interactive exploration of large scale AI datasets, LanceDB is the best foundation for your AI application.
- Website
-
http://lancedb.com
External link for LanceDB
- Industry
- Information Services
- Company size
- 11-50 employees
- Headquarters
- San Francisco, California
- Type
- Privately Held
- Founded
- 2022
Locations
-
Primary
San Francisco, California, US
Employees at LanceDB
Updates
-
𝗖𝗮𝗺𝗯𝗿𝗶𝗮𝗻-𝟭: 𝗩𝗶𝘀𝗶𝗼𝗻-𝗖𝗲𝗻𝘁𝗿𝗶𝗰 𝗦𝗲𝗮𝗿𝗰𝗵 Cambrian-1 is multimodal LLMs (MLLMs) designed with a 𝘃𝗶𝘀𝗶𝗼𝗻-𝗰𝗲𝗻𝘁𝗿𝗶𝗰 capabilities. This example demonstrates 𝗩𝗶𝘀𝗶𝗼𝗻-𝗖𝗲𝗻𝘁𝗿𝗶𝗰 𝗘𝘅𝗽𝗹𝗼𝗿𝗮𝘁𝗶𝗼𝗻 𝗼𝗻 𝗶𝗺𝗮𝗴𝗲𝘀 𝗼𝗯𝘁𝗮𝗶𝗻𝗲𝗱 𝗳𝗿𝗼𝗺 𝘃𝗲𝗰𝘁𝗼𝗿 𝘀𝗲𝗮𝗿𝗰𝗵. It is 2 step process 1. Performing vector search to get related images 2. Use obtained images for Vision-centric Exploration 📄 Detailed Blog - https://lnkd.in/gQ8DkfXz 🔨 Notebook - https://lnkd.in/gwRw5_zP 🌟 Checkout other multimodal examples - https://lnkd.in/gYy6BhgJ #multimodal #computervision #vectorsearch #vectordb #cambrian
-
-
𝐃𝐞𝐯𝐞𝐥𝐨𝐩 𝐐&𝐀 𝐛𝐨𝐭 𝐟𝐨𝐫 𝐜𝐨𝐝𝐞 𝐝𝐨𝐜𝐮𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 This Q&A bot will allow you to query your own documentation. It also demonstrate the use of LangChain and LanceDB using the OpenAI API. This example will use Numpy 1.26 documentation, but, this could be replaced for your own docs as well. 🔨 Try it in Colab - https://lnkd.in/gFArC4Pf 🌐 Try in JS - https://lnkd.in/dfRBYsCV 🌟 Checkout other chatbot examples - https://lnkd.in/gYcTi2RP #qabot #chatbot #documentation #vectordb
-
We're thrilled to see LanceDB's robust search and retrieval capabilities powering platforms like Harvey, enabling seamless and secure processing of complex documents at scale. Thank you, Gabe Pereyra, and the team for trusting LanceDB to help drive Harvey's platform forward! #AI #TechInnovation #DataProcessing #LanceDB #Harvey #Scalability #Security #LegalTech #vectordb
-
-
�� Congratulations to Tullie Murrell and the team at Shaped on your Series-A funding! Hear from Tullie on why LanceDB was a clear winner for them when building Shaped!
-
-
Vector Arithmetic Vector embeddings represent word meanings and relationships, allowing us to add or subtract them to gain insights. This example perfectly demonstrates, adding vectors combines word meanings, while subtracting vectors reveals word relationships. 🔨 Try on Colab - https://lnkd.in/gZEjrX37 📄 Detailed Blog - https://lnkd.in/gzfzGTAk 🌟 Checkout other vector search examples - https://lnkd.in/gjkfMrKa #vectorsearch #embeddings #multimodal #vectordb #vectorarithmetic
-
-
Healthcare Chatbot This project introduces a healthcare RAG chatbot designed to quickly answer medical questions. It uses OpenBioLLM-Llama3 / OpenAI LLM and NeuML's #PubMedBERT for embedding, making it skilled at handling medical data queries. 🔨 Github - https://lnkd.in/dmrTzeP5 🌟 Checkout other applications - https://lnkd.in/gcwRaRyn #chatbot #healthcare #rag #llama3 #vectordb
-
-
LanceDB reposted this
📚 Interested in building a support chatbot from scratch? Check this blog post by Agustín Piqueres Lajarín It covers: - Build a document base from a Github repo - Generate synthetic data to specialize a sentence-transformers model with the new fine-tuning API. - Curate the data with Argilla - Set up a LanceDB vector database - Deploy your chatbot with Gradio on Hugging Face Spaces Link in the comments
-