Examples
- Pyvespa examples
- Multi-vector indexing with HNSW
- Create the application
- Configure fields
- Configure rank profiles
- Configure fieldset
- Configure document summary
- Export the configuration
- Download model files
- Deploy the application
- Feed documents
- Simple retrieve all articles with undefined ranking
- Traditional keyword search with BM25 ranking on the article level
- Semantic vector search on the paragraph level
- Hybrid search and ranking
- Hybrid search and filter
- Cleanup
- Building cost-efficient retrieval-augmented personal AI assistants
- Turbocharge RAG with LangChain and Vespa Streaming Mode for Partitioned Data
- TLDR; Vespa streaming mode for partitioned data
- Connecting LangChain Retriever with Vespa for Context Retrieval from PDF Documents
- Configure Vespa Cloud date-plane security
- Configure Vespa Cloud control-plane security
- Deploy to Vespa Cloud
- Processing PDFs with LangChain
- Querying data
- Interact with the chain
- LightGBM: Training the model with Vespa features
- LightGBM: Mapping model features to Vespa features
- Exploring the potential of OpenAI Matryoshka 🪆 embeddings with Vespa
- Chat with your pdfs with ColBERT, langchain, and Vespa
- TLDR; Vespa streaming mode for partitioned data
- Connecting LangChain Retriever with Vespa for Context Retrieval from PDF Documents
- Configure Vespa Cloud date-plane security
- Configure Vespa Cloud control-plane security
- Deploy to Vespa Cloud
- Processing PDFs with LangChain
- Querying data
- Interact with the chain
- BGE-M3 - The Mother of all embedding models
- Using Cohere Binary Embeddings in Vespa
- Billion-scale vector search with Cohere binary embeddings in Vespa
- Multilingual Hybrid Search with Cohere binary embeddings and Vespa
- Using Mixedbread.ai embedding model with support for binary vectors
- Standalone ColBERT with Vespa for end-to-end retrieval and ranking
- Standalone ColBERT + Vespa for long-context ranking
- Feeding performance
- Using Mixedbread.ai cross-encoder for reranking in Vespa.ai
- Evaluating retrieval with Snowflake arctic embed