Fetch the available thematic categories from the Open Knowledge Graphs catalog to filter searches and compare coverage across datasets.
MIT
523,841 tools. Updated 2026-09-06 14:24
"Understanding Document Embeddings, Knowledge Graphs, and Vector Representations" matching MCP tools:
- Generate vector embeddings from text for semantic search, RAG, clustering, or similarity tasks. Choose between query or document input type and adjust model quality and dimensionality.MIT
- Refresh embeddings and reindex content by synchronizing a knowledge base. Provide the unique ID to update its state.MIT
- Generate 1024-dimensional dense vector embeddings for multilingual and long text using BAAI BGE-Large. Accepts single text or array of texts for semantic search and NLP tasks.MIT
- Find similar vector embeddings in Zilliz Cloud collections using vector similarity search with optional filtering and result customization.Apache 2.0
- Generate text embeddings (vector representations) using OpenAI-compatible models, with support for x402 wallet or API key authentication.MIT
Matching MCP Servers
- AlicenseBqualityAmaintenanceEnables building and querying vector-based knowledge graphs with node and edge management and semantic search.513MIT
- AlicenseAqualityCmaintenanceA minimal MCP server that exposes Gemini's web and multimodal understanding (video, audio, document, image) through five dedicated tools.51MIT
Matching MCP Connectors
AI reasoning checks any document against known international standards before your agent acts on it.
Make your knowledge agent-ready. Connect docs from Confluence, Notion, GitHub, Dropbox, or Google Drive — any AI agent searches them via one MCP endpoint. 3 retrieval modes: vector search, broad search, and full document access. The agent decides how deep to dig.
- Semantically search the SHOAL oracle and fleet vector index for patterns, crates, solutions, and knowledge. Returns ranked results with conservation metadata.MIT
- Delete a knowledge document from Anam AI using its unique ID. Removes the specified document from your knowledge base.MIT
- Remove a knowledge document from the system by specifying its document ID.MIT
- Retrieve the download URL for a knowledge document by providing its unique document ID.MIT
- Generate 768-dimensional dense vector embeddings from text to enable RAG and semantic search. Accepts single strings or batches, converting them into vector representations via BAAI BGE-Base.MIT
- Store typed knowledge (observation, decision, learning, error, pattern) with tags, importance, and optional relation. Embeddings enable semantic retrieval.MIT
- Preview what will be removed (chunks, images) from the RAG knowledge base, then confirm to delete the document and all associated data.MIT
- Retrieve verified firearms information from Woody's knowledge base using vector search. Get raw document chunks with relevance scores for fact-checking or finding specifications.MIT
- Updates the vector index with current knowledge base docs. Re-embeds changed files by default; use force to rebuild all embeddings from scratch after changing the embedding model.Business Source 1.1
- Store precomputed embedding vectors for multiple requirements in one call, keeping requirement text private and data local. Ensures consistent vector dimensions across all stored embeddings.MIT
- Retrieve and filter knowledge graphs to obtain graph IDs and node information for subsequent operations like adding edges or querying node details.MIT
- Create and manage per-team knowledge bases with vector-indexed documents. Agents search via hybrid cosine similarity and keyword fallback at runtime.AGPL 3.0Destructive
- Rebuild vector embeddings for semantic and hybrid search. Default converges the index to the current vault; force=true rebuilds from scratch after changing the embedding model.MIT
- Search past sessions by meaning using vector embeddings. Finds contextually similar sessions even when exact wording differs.Apache 2.0
- Generate numerical vector embeddings for text inputs, enabling semantic search, clustering, deduplication, or retrieval-augmented generation. Returns one embedding array per text in input order.MIT