Bindex Core 1.4.2-SNAPSHOT API

Bindex Core

Bindex Core provides core functions for managing Bindex metadata, including library generation, registration, selection, and project building. It enables automated processing of library metadata to support efficient application discovery, integration, and assembly workflows. A Bindex descriptor records a component's identity, version, description, dependencies, and technical classification.

The bindex-core project provides core functions for managing Bindex metadata, including library generation, registration, selection, and project building. Its purpose is to automate library-metadata processing for efficient application discovery, integration, and assembly workflows.

Bindex Core supports all types of project files, including source code, documentation, project site content, and other relevant files, when generating, registering, and processing project metadata.

Architecture

A Bindex descriptor represents a library or integration and its classification metadata. The core package separates persistence and semantic search behind the BindexRepository interface. MongoBindexRepository implements that boundary with MongoDB, storing serialized descriptors together with searchable classification fields and embedding vectors. Picker uses configured GenAI and embedding providers to classify a natural-language request, create a query embedding, find matching descriptors, register entries, and resolve dependencies. Recommendation results are returned as compact BindexInfo values containing identity, version, description, and similarity score.

The AI tools package adapts this workflow for AI hosts. BindexFunctionTools exposes Functional AI Tools for retrieving, recommending, and registering descriptors, as well as the Bindex JSON Schema Contextual Resource and descriptor-generation Prompt Template. GraphqlJsonFilter supports retrieval by projecting requested top-level fields from a serialized descriptor. This keeps AI-host integration separate from core repository and recommendation services.

The following diagram shows the principal types and their relationships:

Packages

org.machanism.machai.bindex.core

Provides Bindex persistence, semantic search, recommendation, registration, and dependency resolution. Use BindexRepository as the persistence boundary, MongoBindexRepository for MongoDB-backed storage and vector search, and Picker to classify requests and select matching libraries.

org.machanism.machai.bindex.ai.tools

Provides the AI-facing adapter layer. BindexFunctionTools makes descriptor retrieval, recommendation, and registration available as Functional AI Tools and exposes the Bindex JSON Schema Contextual Resource and generation Prompt Template; GraphqlJsonFilter projects selected top-level descriptor fields for GraphQL requests.

Using Bindex Core

Configure a Configurator with MongoDB, GenAI-provider, and embedding-provider settings. Construct a MongoBindexRepository, provide it to a Picker, and submit a natural-language request with a result limit and minimum similarity score. The picker returns BindexInfo summaries; use the repository to retrieve a complete descriptor by identifier when necessary. Close a MongoDB repository after use to release its client resources.

For AI-host integration, register BindexFunctionTools with the Function Tools host. The host can discover the named Functional AI Tools, Prompt Template, and Contextual Resource from their annotations, while the tools delegate persistence and recommendations to the core services.

Packages

Package	Description
org.machanism.machai.bindex.ai.tools	Provides the AI-facing integration layer for Bindex (bundle index) metadata.
org.machanism.machai.bindex.core	Supplies persistence, semantic search, and recommendation services for Bindex metadata.