giusedroid / serverless-embeddings-lancedb-bedrock
This is an example of serverless document ingestion pipeline that automates the calculation of embeddings, so that they can be used in the context of a Retrieval Augmented Generation application. This sample makes use of Amazon Bedrock to provide access to Amazon Titan Embedding model and LanceDB
☆27Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for serverless-embeddings-lancedb-bedrock
- Flexible and powerful framework for managing multiple AI agents and handling complex conversations☆190Updated this week
- Explore sample applications and tutorials demonstrating the prowess of Amazon Bedrock with Python. Learn to integrate Bedrock with databa…☆120Updated last week
- ☆87Updated 10 months ago
- Use LLMs for building real-world apps☆109Updated 2 weeks ago
- AI real estate agent☆31Updated 9 months ago
- aws-solutions-library-samples / guidance-for-conversational-chatbots-using-retrieval-augmented-generation-on-awsThis Guidance demonstrates how to combine Retrieval Augmented Generation (RAG) with AWS services to build generative AI applications.☆34Updated 3 weeks ago
- ☆32Updated 9 months ago
- ☆37Updated 2 weeks ago
- Deploy llama.cpp compatible Generative AI LLMs on AWS Lambda!☆169Updated 6 months ago
- Applying the latest advancements in AI and machine learning to solve complex business problems.☆73Updated 7 months ago
- API playground for Deepgram built with Streamlit☆20Updated 6 months ago
- Adding NeMo Guardrails to a LlamaIndex RAG pipeline☆35Updated 8 months ago
- Build Generative AI applications with Langchain on AWS☆171Updated last year
- Creating Amazon Bedrock agents with Streamlit Framework☆90Updated 2 weeks ago
- ☆179Updated last year
- A pattern to let you try several vector databases and change a little code as possible☆37Updated last year
- ☆20Updated last year
- ☆115Updated this week
- ☆59Updated 2 months ago
- Amazon Bedrock Foundation models with Amazon Opensearch Serverless as a Vector DB☆148Updated this week
- Generate Tools and Toolkits from any Python SDK -- no extra code required☆50Updated last week
- Samples to build Generative AI applications with LangChain and Amazon Kendra☆159Updated 6 months ago
- Pinecone AWS Reference Architecture☆103Updated last week
- An agent based LLM assistant that extends RAG with batch entity extraction and SQL querying to improve performance on multi-step and anal…☆58Updated 4 months ago
- ☆222Updated 4 months ago
- Demonstration application showing how Neo4j works with Amazon Bedrock☆49Updated 7 months ago
- This project presents a RAG chat app for the Speckle Developer Documentation.☆29Updated 4 months ago
- Contextual Doc Retrieval is a Python-based system leveraging OpenAI GPT-4o and Cohere for re-ranking and query expansion, combined with B…☆34Updated 3 weeks ago
- Automated knowledge graph creation SDK☆110Updated 4 months ago
- A full-stack serverless RAG workflow. This is thought for running PoCs, prototypes and bootstrap your MVP.☆49Updated last week