Obsidian Smart Connections

This project is a knowledge base plugin and RAG context manager that uses a local vector database interface to enable semantic search and relationship mapping. It transforms text into numerical vectors to find semantically related notes and excerpts based on conceptual meaning rather than keyword matches.

The system differentiates itself through a semantic graph visualizer that maps notes into clusters to reveal conceptual connections. It also features a context manager capable of bundling local notes and excerpts into reusable packs to provide grounded factual bases for large language model conversations.

The tool covers a wide range of capabilities including natural language knowledge querying, automated workflow execution for note creation, and the ability to route prompts between local and cloud-based AI models. It provides several discovery interfaces, such as inline related content indicators and a footer panel for surfacing similar documents during the editing process.

Features

Vault Chat Interfaces - Provides an AI chat interface that utilizes a personal knowledge vault as context for conversations.
Private Document Search Engines - Provides a private search engine that indexes and retrieves information from local documents using vector databases.
Embedding-Based Note Searches - Enables natural language querying to find relevant notes using local vector embeddings.
Agent Context Providers - Provides systems that inject relevant documentation and local file context into an agent's workspace.
Project Documentation Grounding - Provides selected notes as a factual basis to guide and ground the responses of a language model.
Context-Window Aggregators - Aggregates selected note excerpts and blocks into structured text to serve as grounded AI context.
Local Embedding Generators - Generates vector embeddings for text locally on the machine to ensure private semantic search.
Prompt Assembly Systems - Dynamically constructs AI prompt context by aggregating curated collections of notes and blocks.
RAG Context Retrieval - Retrieves relevant document segments from a local knowledge base to ground LLM responses.
Semantic Similarity Calculation - Calculates mathematical relationships between texts to determine similarity in meaning for surfacing connected ideas.
Semantic Cluster Relationship Mapping - Visualizes the distance and relationship between semantic clusters of notes in a 2D space.
Semantic Vector Search - Retrieves notes based on the mathematical distance between query and document embeddings.
Semantic Text Matching - Uses semantic text matching to select the most relevant search results as input for AI tasks.
Natural Language Querying - Provides an interface to retrieve information from the knowledge vault using natural language questions.
Automatic Note Discovery - Automatically surfaces semantically similar notes based on the current document to facilitate discovery.
Folder-Based Context Assemblers - Assembles relevant notes from selected folders and tags into single context packs for AI analysis.
Local Document Indexing - Indexes local file systems into vectors to enable private information retrieval for RAG applications.
Natural Language Search - Implements search capabilities that use natural language queries to retrieve blocks based on conceptual meaning.
Knowledge Base Bundles - Combines related search results into reviewable sets to provide grounded knowledge bases for AI workflows.
Document Search Grounding - Grounds AI responses using content from a local index of documents and notes.
Semantic Document Retrieval - Surfaces semantically similar excerpts based on the active document to discover relevant prior work.
AI-Enhanced Markdown Bases - Provides a markdown-based knowledge base that uses a local embedding model to find semantically related notes.
Grounded Context Retrieval - Provides systems for querying indexed data collections to provide source-attributed context for AI workflows.
Search Result Optimizations - Optimizes result order using a combination of similarity scoring and metadata weights.
Semantic Search - Identifies and displays semantically relevant excerpts from the vault based on the active note content.
Vector Databases - Implements a local database optimized for storing and querying high-dimensional vector embeddings.
AI-Based Relevance Ranking - Uses learned model embeddings to order notes and excerpts based on semantic relevance.
Cross-Context Bundling - Bundles relevant excerpts from various folders into reviewable sets to ground AI prompts.
Knowledge Graph Visualizations - Visualizes conceptual relationships and semantic clusters as networked nodes and edges.
Metadata-Driven Relevance Weighting - Adjusts relevance scores based on key-value pairs in frontmatter or substring matches in paths.
Relevance Scoring - Calculates numerical relevance scores for notes within a collection relative to a reference note.
Knowledge Session Managers - Stores selected sets of content under a name so they can be reopened across different sessions.
AI Chat Actions - Executes local actions like note creation and task triaging directly from a chat interface.
Semantic Discovery Engines - Uses semantic indexing to surface related notes and excerpts while the user is writing.
Automation Workflows - Uses chat interfaces and local models to automate note creation and task triaging.
Conversation History Persistence - Saves and restores the state of interactive AI chat sessions within the local knowledge base.
Note-to-Thread Mappings - Links unique chat thread identifiers to specific notes to maintain stateful discussions across documents.
Semantic Relationship Visualizers - Visualizes the semantic distance and clustering between notes to reveal conceptual connections.
Contextual Note Surfacing - Displays related notes as inline markers or sidebars while editing.
Weighted Similarity Aggregation - Combines vector similarity with weights from file paths and metadata to refine search rankings.
Structured Prompt Templates - Uses structured templates to combine active content into ready-to-run AI prompts.
Conversation Thread Contexts - Maintains persistent conversation state and history across interactions using a dedicated thread model.
Document-Linked Conversations - Attaches chat threads to specific documents so discussions can be resumed from the original context.
AI-Focused Excerpt Collection - Filters relevant snippets from search results to provide focused information for AI prompts.
Semantic Neighborhood Mapping - Maps notes into visual neighborhoods to reveal conceptual relationships that list-based results cannot show.
Dynamic Context Synchronization - Links folders or tags to a saved context so bundles update automatically as new content is added.
External Data Integrations - Incorporates data from external files and repositories to enrich the semantic retrieval process.
Rank-Based Result Refinements - Tunes ranking by penalizing hidden notes or boosting candidates similar to pinned references.
Semantic Association Linking - Converts semantic matches into direct links within a document to connect related information.
Search Result Filtering - Hides irrelevant matches or pins important references to refine the quality of results.
Text-Based - Converts curated collections of blocks into merged text strings or link trees for external use.
Knowledge Relationship Graphs - Renders a graph of related notes to identify clusters and the overall structure of a topic.
Semantic Link Filtering - Filters semantic links to ensure only the most relevant notes appear in complex vaults.
Recency Prioritization - Prioritizes the most recently modified items among semantically relevant matches.

logancyang/obsidian-copilot

6,211View on GitHub

Obsidian Copilot is an AI assistant plugin for Obsidian that brings conversational AI directly into your note-taking vault. It allows you to chat with multiple large language models, create and execute custom prompts, and edit notes through natural conversation, all without leaving your workspace. The plugin distinguishes itself by offering complete model flexibility, supporting OpenAI, Anthropic, Google, local, and self-hosted models with no vendor lock-in. It stores all chat history, system prompts, and custom commands as plain Markdown files in your vault, ensuring full data ownership and

lancedb/lancedb

9,031View on GitHub

LanceDB is a vector database and columnar data store designed to function as a versioned dataset manager and vector search engine. It serves as a high-performance backend for indexing and retrieving high-dimensional embeddings, providing the foundation for machine learning data pipelines. The system distinguishes itself through a combination of cloud-native object storage and immutable version tracking, allowing for data time-travel and reproducible AI experiments. It integrates hybrid search capabilities, merging dense vector similarity with BM25 full-text search and SQL-like scalar filters

BasedHardware/omi

12,869View on GitHub

Omi is an open-source wearable AI platform that captures audio and screen data to provide real-time conversational assistance and memory. It integrates a wearable hardware development kit with a vector memory database and large language model capabilities to create a persistent digital record of user interactions. The platform is distinguished by its BLE audio streaming pipeline, which transmits raw audio from wearable hardware for real-time transcription and speaker identification. It utilizes a plugin-based agent tool framework that allows AI assistants to autonomously invoke custom functio

marqo-ai/marqo

5,022View on GitHub

Marqo is an ecommerce product discovery platform, multimodal vector database, and AI search merchandising tool. It provides infrastructure for implementing semantic search and recommendations, allowing shoppers to find products using natural language and images. The platform distinguishes itself through a hybrid ranking pipeline that combines neural semantic scores with business-defined boosting and pinning rules. It features a conversational commerce engine that uses large language models to process user intent and provides a search performance analytics suite for measuring conversion uplift

brianpetroobsidian-smart-connections

Features