brianpetro/obsidian-smart-connections

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.

Star-Verlauf