Add files to a RAG system for document retrieval, supporting PDF, DOCX, TXT, MD, CSV, and JSON formats to enable semantic search and information access.
MIT
466,097 tools. Updated 2026-08-19 11:06
"Slack Bot with RAG Document Retrieval and Automated Response System" matching MCP tools:
- Create a searchable knowledge base from plain text, automatically chunked and indexed for RAG retrieval. Ideal for FAQs, product specs, and policies.MIT
- Create a named document collection to group related evidence bundles for cross-document semantic search and RAG-based Q&A.MIT
- Perform semantic search over a stored memory namespace to retrieve the most relevant entries. Use this to recall context for RAG pipelines.MIT
- Verify that an LLM response engaged with the provided source document using the Semantic Grounding Index score. Ideal for auditing RAG pipeline provenance.Apache 2.0
- Index new strategy research, marketplace listings, blueprints, skills, and bot logs into a self-hosted Onyx RAG host by triggering an incremental ingest.MIT
Matching MCP Servers
- AlicenseBqualityDmaintenanceEnables retrieval-augmented generation by embedding queries with a chosen provider (e.g., OpenAI) and searching supported vector stores (Pinecone, pgvector) to return relevant content.1Apache 2.0
- Flicense-qualityCmaintenanceEnables AI coding assistants to query private academic paper collections via standard MCP tools, with hybrid retrieval, reranking, and inline citations.
Matching MCP Connectors
Cloudflare Workers MCP server: api-response-cost-analyzer
Enable interaction with Slack workspaces. Supports subscribing to Slack events through Resources.
- Get RAG corpus statistics: document counts, hostnames, coverage. Use this to evaluate the scope and completeness of your content knowledge base.MIT
- List documents and web pages ingested into a knowledge store for RAG retrieval, with pagination and filtering.MIT
- Retrieve text segments (chunks) from a knowledge store for RAG retrieval, with optional pagination, filtering by text or source.MIT
- Add knowledge entries to a RAG system to store insights, tips, and best practices. Categorize and tag them for efficient retrieval.MIT
- Index a document by ID and text for keyword search retrieval. Add documents to make them searchable across sessions.MIT
- Evaluate retrieval quality by running test queries and checking expected document ranking. Returns MRR@5 and Recall@5 to audit search effectiveness after ingestion or tuning.MIT
- Retrieve connected Slack workspace name, team ID, and bot user ID to verify Slack integration status.MIT
- Query an AI Knowledge project with RAG to get LLM answers or retrieve document chunks as context.
- Run faithfulness and retrieval quality evaluation over a batch of RAG pipeline cases, producing a summary report with mean metrics and worst-performing cases.MIT
- List public Slack channels accessible to the bot, returning id, name, and member count. Optionally limit the number of channels returned.MIT
- Retrieve top-k passages from a sample RAG corpus using various retrieval methods to see what context a RAG system would surface for a query.MIT
- Generate embedding vectors for semantic search, RAG retrieval, and similarity scoring using IBM Granite models. Supports up to 64 texts per call with no IBM Cloud account required.Apache 2.0
- List document categories in the knowledgebase, returning each category's UUID and document count. Use these IDs when creating or updating documents, or to scope ask_ai retrieval.MIT
- Ingest text content into a governed retrieval system with integrity verification and audit trail. Documents are chunked, embedded, and hash-verified for trustworthy retrieval.Inno Setup