Trieve
Trieve provides an all-in-one infrastructure for vector search, recommendations, retrieval-augmented generation (RAG), and analytics, accessible via API for seamless integration.
About this tool
Trieve
Category: Vector Database Engines
Tags: open-source, vector-search, rag, analytics
Source: GitHub - devflowinc/trieve
Description
Trieve provides an all-in-one infrastructure for vector search, recommendations, retrieval-augmented generation (RAG), and analytics, accessible via API for seamless integration.
Features
- Self-Hosting: Full guides available for deploying in VPC, on-prem, AWS, GCP, Kubernetes, or via Docker Compose.
- Semantic Dense Vector Search: Integrates with OpenAI or Jina embedding models and Qdrant for semantic search capabilities.
- Typo Tolerant Full-Text/Neural Search: Uses naver/efficient-splade-VI-BT-large-query for typo-tolerant, neural sparse-vector search.
- Sub-Sentence Highlighting: Highlights and bolds matching words/sentences in search results for improved UX.
- Recommendations API: Find similar content chunks or files, useful for platforms with content interactions (favorite, bookmark, upvote).
- RAG API Routes: Integrates with OpenRouter, provides fully-managed RAG with topic-based memory or custom context RAG, and supports any LLM.
- Bring Your Own Models: Supports custom text embedding, SPLADE, cross-encoder re-ranking, and LLMs.
- Hybrid Search: Combines vector search with cross-encoder re-ranking for improved results (e.g., BAAI/bge-reranker-large).
- Recency Biasing: Option to bias search results towards recent content.
- Tunable Merchandizing: Adjust search relevance using signals like clicks, add-to-carts, or citations.
- Filtering: Supports date-range, substring, tag, numeric, and other filters.
- Grouping: Group multiple chunks as part of the same file; search can be performed at file-level to avoid duplicate top-level results.
- Analytics: Infrastructure includes analytics components (details not specified in content).
- Multiple SDKs: API access via Typescript and Python SDKs.
- Local Development Support: Guides and scripts provided for local setup and development.
Pricing
No explicit pricing details provided in the content. There is mention of Stripe integration for product and plan creation, indicating the possibility of paid plans, but no actual plan details are specified.
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)ClickHouse is an open-source column-oriented database that supports vectorized computation and now offers vector search features. Its architecture enables efficient real-time analytics and vector operations, making it a relevant choice for vector database use cases.
OpenSearch is a fully open-source, community-driven search and analytics suite that supports vector search, providing a transparent and flexible alternative for organizations seeking advanced search features.
Qdrant is a dedicated vector database and similarity search engine supporting advanced filtering and efficient retrieval, suitable for faceted search and retrieval-augmented generation. It offers self-hosted and cloud deployment options, making it highly relevant for vector search applications.
HelixDB is a powerful, open-source graph-vector database built in Rust, designed for intelligent data storage for Retrieval-Augmented Generation (RAG) and AI applications. It combines graph database features with vector search, making it directly relevant to AI and machine learning workflows that require vector data management.
A distributed vector database designed for scalable and efficient vector similarity search. It is purpose-built for handling large-scale vector data and search workloads.
Cottontail DB is an open-source vector database for storing and searching high-dimensional data, with features geared towards research and production environments.