Search uploaded documents using RAG to find answers with citations. Ask questions to retrieve information from your knowledge base.
MIT
127,483 tools. Last updated 2026-05-05 17:17
"Information on RAG Documents or Processing" matching MCP tools:
- Find relevant documents in the RAG system using semantic search with customizable similarity thresholds and result limits.MIT
- Execute a complete RAG workflow in a single step to answer user questions: generate embeddings, perform semantic search, and answer using only retrieved context.
- Extract structured data from documents using custom or auto-generated schemas to process various file formats including PDF, images, and Office documents.MIT
- Filter documents by metadata before ranking by vector similarity to enable production RAG and semantic search pipelines.MIT
- Retrieve detailed form template information to examine structure and field specifications before creating documents or new forms in RSpace.AGPL 3.0
Matching MCP Servers
- Alicense-qualityCmaintenanceAn MCP server that enables AI assistants to create and run Processing sketches directly through natural language commands.Last updated4MIT
Matching MCP Connectors
ship-on-friday MCP — wraps StupidAPIs (requires X-API-Key)
Image processing for AI agents. Resize, convert, compress, and pipeline images.
- Add documents to a collection by providing a URL for download, processing them for text extraction, and indexing them for semantic search.MIT
- Retrieve and filter team documents in BoldSign by status, user, team, date range, or search terms to manage organizational document workflows.MIT
- Remove specific documents from a Chroma collection by specifying their IDs and collection name. Confirms the number of documents deleted and handles errors for invalid inputs or non-existent collections.Apache 2.0
- Search documents using semantic understanding to find relevant content based on meaning rather than keywords. Understands natural language queries and returns ranked passages with source information.MIT
- Find documents based on their position in a folder hierarchy by providing keywords for each path level. Returns matching document filings.Apache 2.0
- Retrieve statistical metrics about a collection's documents, processing status, storage usage, and index health to monitor readiness and verify completion.MIT
- List documents in a Needle collection to check processing status, inventory available files, and verify document availability before searching.MIT
- Check BOM processing status and identify unknown or unmatched parts. Unknown components are highlighted for attention after processing completes.Apache 2.0
- Retrieve detailed information about a Heroku add-on, including plan state, billing details, and configuration. Supports identifiers like add-on ID, name, or attachment name, requiring app context for attachments.
- Stores a knowledge fragment with source and evidence tier metadata for future retrieval via semantic RAG queries.MIT
- Sort documents by their relevance to a specific query using Jina AI's reranking technology. Organize search results or content collections to prioritize information that best matches your topic.Apache 2.0
- Retrieve detailed information about a media file, including type, dimensions, size, upload status, and aspect ratio. Check if the file has finished processing before attaching to a post.
- Modify documents in a Chroma collection by updating embeddings, metadatas, or text content. Ensure data integrity by matching input IDs with provided updates for accurate modifications.Apache 2.0
- Search for documents by name using keywords and optional class filter. Returns matching documents with confidence scores to help select the correct one.Apache 2.0