An enhanced client for Ollama that now handles image data for VLM models.

A recursive chunker that splits Markdown text based on its semantic structure and embeds document-level metadata into each chunk.

Handles the indexing of vector embeddings and rich metadata into LanceDB. The 'text' field is the content that gets embedded (which can be en

The main agent, now fully wired to use a live Ollama client.

Generic batch processor with progress tracking and error handling

Tracks progress and performance metrics for batch operations

An embedding model that uses a local Hugging Face transformer model.

A client for IBM Watson X AI that provides similar interface to OllamaClient for seamless integration with the RAG system.

A reranker that uses a local Hugging Face transformer model.

Demonstration of batch indexing capabilities.

Custom formatter with colors for different log levels and services.

Enriches chunks with a prepended summary of their surrounding context using Ollama, while preserving the original text.

A class to convert various document formats to structured Markdown using the docling library. Supports PDF, DOCX, HTML, and other formats.

Extracts entities and relationships from text chunks using a live Ollama model.

Interactive index creation utility.

Generate late-chunked embeddings given character-offset spans.

A wrapper for a local vision model (ColPali) from the transformers library.

Performs hybrid (vector + FTS) or vector-only retrieval.

Processes PDFs into separate text and image embeddings using local models.

Call Ollama's /api/embeddings endpoint for each text.

Generates and stores a one-paragraph overview for each document. The overview is derived from the first *n* chunks of the document.

Enhanced ProgressTracker that sends updates via Server-Sent Events

Orchestrates the state-of-the-art multimodal RAG pipeline.

Lightweight singleton wrapper around the Provence model.

Manages multiple system services with logging and health monitoring.

Verifies if a generated answer is grounded in the provided context using Ollama.

Enhanced API handler with progress tracking support

Handler for Server-Sent Events (SSE) for real-time progress updates

Process items one at a time with minimal memory usage