Ground AI and agents in enterprise data

Agentic retrieval is retrieval that an AI agent directs. The agent decides when to search, which datasets to query, and how to refine a query after it reads the results. In Spice, agents call the built-in search and sql tools through the MCP server gateway or through a model with tools: auto.

RAG reduces hallucinations by grounding model responses in data retrieved at query time instead of relying only on training data. Models grounded in incomplete or outdated data are more likely to hallucinate, so retrieval quality and freshness matter as much as the model itself. Spice retrieves live, governed data with SQL and hybrid search so the context passed to the model stays accurate.

Hybrid search runs vector similarity search and BM25 full-text search in parallel. Reciprocal Rank Fusion (RRF) then merges the two ranked lists into one result. You call it through the /v1/search API or with the vector_search() and text_search() SQL functions. Results are tables, so you can filter, join, and aggregate them like any other dataset.

No. Spice creates embeddings with local or hosted models and runs vector similarity search inside the runtime. A vector database usually needs other systems for text search, keyword search, and joins with structured data. Spice runs all of these in one runtime that you can deploy locally, in your cloud, or as a managed service.

Yes. Spice federates queries across databases, object stores, and APIs with standard SQL. One query can retrieve structured records and combine them with semantic search results. This grounds model responses in operational data without manual data engineering.

Spice invokes models from providers like OpenAI and Anthropic, or local LLMs, through its AI Gateway. Models are called directly in SQL, so retrieved context feeds into generation within the same query workflow. SQL AI functions also classify, label, summarize, and score the sentiment of search results. See LLM inference and AI model serving for how model serving works in Spice.

Spice blends multiple result sets with Reciprocal Rank Fusion (RRF). Each query can set a weight per search, add SQL filters, and boost recent rows. Weight keyword precision for exact lookups, semantic matches for natural-language questions, or recency where freshness matters.

Spice materializes hot data locally with DuckDB, SQLite, or Spice Cayenne acceleration. Large vector indexes can live in Amazon S3 Vectors, which fits millions or billions of embeddings that do not need always-on compute. Index-only reads and filter pushdown keep common queries predictable under high concurrency.