18 docs tagged with "Search"

Configure the Cohere reranker in Spice to rerank search results with the Cohere API.

Query Elasticsearch indexes as SQL tables in Spice, including kNN vector search, full-text search, and hybrid search.

Operating guide for the Elasticsearch data connector in production: authentication, TLS, resilience, and operational tuning.

Describes how embedding models are used in Spice to convert text into numerical vectors for machine learning and search applications.

Load a cross-encoder reranker from a local directory and run it in Spice.

Learn how Spice can perform full text search

Connect Spice to a self-hosted or third-party reranker service over HTTP with a Cohere-compatible rerank schema.

Download a cross-encoder reranker from the Hugging Face Hub and run it locally in Spice.

Configure the Jina AI reranker in Spice to rerank search results with the Jina AI API.

Use a chat model or a decision model from the models section as a reranker, with no reranker configuration.

Embed list-of-strings columns as a column of vectors and use ColBERT-style late-interaction search in Spice.

Overview of the reranker model providers that Spice supports to reorder search results by relevance.

Rerank search results using dedicated reranker models, chat models, or decision models for improved relevance.

Learn how Spice can search across datasets using database-native and vector-search methods.

Reduce per-turn token cost and improve LLM tool selection accuracy by replacing individual tool definitions with searchable tool_search and tool_invoke meta-tools backed by hybrid full-text, keyword, schema, and vector search.

Learn how Spice can perform searches using vector-based methods.

Configure the Voyage AI reranker in Spice to rerank search results with the Voyage AI API.

Learn how Spice can perform web search