v1.2.2

What's Changed

• release(ragbits-core): update to v1.2.2 by @ds-ragbits-robot in #770

Full Changelog: v1.2.1...v1.2.2

v1.2.1

1.2.1 (2025-08-04)

Changed

• ragbits-chat updated to version v1.2.1
• ragbits-cli updated to version v1.2.1
• ragbits-document-search updated to version v1.2.1
• ragbits-evaluate updated to version v1.2.1
• ragbits-guardrails updated to version v1.2.1
• ragbits-core updated to version v1.2.1

v1.2.0

1.2.0 (2025-08-01)

🚀 Enhanced User Experience & Core Improvements

This release delivers a comprehensive upgrade across the entire Ragbits ecosystem, featuring major UI enhancements with image support and conversation history, powerful new agent capabilities with native OpenAI tools integration, advanced core engine improvements including reasoning models and Google Drive integration, plus important stability fixes and performance optimizations.

✨ Key Features & Highlights

Ragbits UI Major Enhancements

• Image Support: Attach images to responses from your chatbot! Ragbits will create a gallery under agent response with all the images.
• Conversation History: In Ragbits 1.2.0 history of conversations can be saved client-side, so your users can go back to the chat they never ended!
• Share Functionality: New share functionality you can copy payload to the clipboard and send it to somebody else - pasting the payload will open exactly the same chat as you
• Parallel Conversations: Support for multiple simultaneous conversations in the UI, enabling users to manage several chat sessions at once.
• Other Improvements:
  • User settings now persist across sessions
  • UI elements on messages behave better when loading
  • Updated Tailwind, React, and Vite
  • More testing

Core Engine Improvements

• Reasoning Models Support: Added support for reasoning models and capturing their thinking blocks.
• Enhanced Attachment API: New API for attaching images / files in prompts.
• Enhanced Usage Tracking: Split usage per model to calculate final cost.
• Google Drive Integration: Added Google Drive Source.
• Batch Generation Support: Added batch generation in LLM, improving performance for bulk operations.

Agent Improvements

• Native OpenAI Tools Support: Direct support for OpenAI's native tools: web_search, code_interpreter, image_generation.
• Agent Context: Added Context object to Agents for easier state management and usage tracking.
• Token-based limits for agents: Agents can now stop their processing when they reach X amount of tokens used.

Bug Fixes & Stability

• Cost Calculation Fixes: Resolved issues with cost calculation for some models.
• Tool Call Arguments: Fixed improper conversion to JSON of tool call arguments.

v1.1.0

1.1.0 (2025-07-09)

🤖 Agent Release

This release brings agentic capabilities to Ragbits, together with major user interface enhancements, expanded observability, new integrations, and core improvements.

✨ Key Features & Highlights

Agents: Easily build agentic systems that proactively interact with their environment.

• Agent Interface: Define agents by combining LLMs, prompts, and tools using the ragbits-agents package. Tool creation is streamlined—simply annotate Python functions, and Ragbits automatically handles type hints and docstrings for agent consumption.
• MCP Server Integration: Connect your agents to hundreds of off-the-shelf tools by running or connecting to an MCP Server, instantly expanding agent capabilities.
• A2A Protocol Support: Enable inter-agent communication with the new A2A Protocol. The Agent.to_a2a() method makes it seamless to register an agent as an A2A Card, share, and communicate via the bundled A2A Server.
• Streaming Responses: All agents now support streaming by default—use Agent.run_streaming() to send results as they’re generated, improving responsiveness and UX.
• Tracing & Observability: Built-in agent tracing support with multiple backends including OpenTelemetry, CLI, and Logfire, making it easy to monitor and debug agent reasoning and tool use.

Ragbits UI Improvements

• User Interface Improvements: Richer, more interactive and customizable chat experiences.
• Live Updates: Real-time notifications from the backend keep users in the loop—see searches, tool calls, and step-by-step reasoning as they happen.
• Message History Navigation: Use up/down arrows to effortlessly navigate and edit previous messages, streamlining user interactions.
• Follow-up Message Suggestions: Applications can now suggest contextual follow-up questions. Show follow-up buttons in the UI by simply calling a backend method.
• TypeScript SDK: Faster custom integrations! Access Ragbits API from your own interfaces using the new TypeScript SDK, available standalone or as React hooks.
• User Settings: Define a Pydantic model to automatically generate a user settings form in the UI. These settings can customize chatbot behavior per-user—making it simple to add personalizable controls.
• Debug Mode: Activate debug mode in the chat UI to view internal chat state, events, and other chatbot internals, greatly aiding development and troubleshooting.

Observability

• Comprehensive OpenTelemetry Metrics: Now supporting all OpenTelemetry metric types for robust, expressive monitoring.
• Server Observability: Improved observability into servers registered or available through RagbitsAPI, surfacing infrastructure insights.
• Grafana Dashboards: New, ready-to-use Grafana dashboards are now bundled with create-ragbits-app for instant monitoring out of the box.
• Logfire Integration: One-line setup to send traces and metrics directly to Pydantic Logfire, enabling comprehensive observability with minimal configuration.

Integrations

• Weaviate VectorStore: Use Weaviate as a fully compatible VectorStore backend across Ragbits components such as document-search.

Developer Experience & Other Improvements

• RagbitsChatClient: Introduced a new RagbitsChatClient for seamless interaction with RagbitsAPI from Python. Makes building custom python clients and integrations easier than ever.

v1.0.0

1.0.0 (2025-06-04)

🎉 Major Release

This is the first stable release of ragbits, marking a significant milestone in the project's development.
The v1.0.0 release represents a mature, production-ready framework for building GenAI applications.

🚀 New Features

ragbits-core

• Vector Store Improvements:
  • Automatic vector_size resolution by PgVectorStore
  • Added get_vector_size method to all Embedders
  • Added support for limiting VectorStore results by metadata
• Embeddings: Refactored BagOfTokens model with model_name/encoding_name parameters moved to init
• Type Safety: Renamed typevars InputT and OutputT to PromptInputT and PromptOutputT for better clarity
• Monitoring: Added Prometheus & Grafana monitoring for LLMs using OpenTelemetry
• File Type Detection: Switched from imghdr to filetype for image file type detection
• Utilities: Added batched() helper method to utils

ragbits-document-search

• Advanced Document Processing: Switch to docling as default document parser for improved document handling
• Batching Support: Added elements batching for ingest strategies to improve performance
• Document Types: Added support for JSONL file type and improved document file type detection
• Reranking Enhancements:
  • Added LLM reranker with optional score override
  • Added score threshold to reranker options
  • Retained score information from vector database or reranker in Element class
• Query Processing: Added query rephraser options for better search results
• Error Handling: Improved error handling for elements without enricher

ragbits-chat

• Persistence Support: Added persistence component to save chat interactions from ragbits-chat with conversation_id parameter support
• State Management: Added support for state updates in chat interfaces with automatic signature generation
• UI Improvements: Refactored UI components to allow modifications and rebuilt UI with new dependencies
• API Integration: Enhanced API integration with history context changes and feedback form integration

ragbits-evaluate

• Question Answering: Added evaluations for question answering tasks
• Dataset Enhancements:
  • Added support for slicing datasets
  • Support for custom column names in evaluation datasets
  • Support for reference document ids and page numbers
• Batch Processing: Adjusted evaluation pipeline interface to support batch processing
• Data Loading: Separated load and map operations in data loaders

v0.20.1

0.20.1 (2025-06-04)

Changed

• ragbits-chat updated to version v0.20.1
• ragbits-cli updated to version v0.20.1
• ragbits-document-search updated to version v0.20.1
• ragbits-evaluate updated to version v0.20.1
• ragbits-guardrails updated to version v0.20.1
• ragbits-core updated to version v0.20.1

v0.20.0

0.20.0 (2025-06-03)

Changed

• ragbits-chat updated to version v0.20.0
• ragbits-cli updated to version v0.20.0
• ragbits-document-search updated to version v0.20.0
• ragbits-evaluate updated to version v0.20.0
• ragbits-guardrails updated to version v0.20.0
• ragbits-core updated to version v0.20.0

v0.19.1

0.19.1 (2025-05-27)

Changed

• ragbits-chat updated to version v0.19.1
• ragbits-cli updated to version v0.19.1
• ragbits-document-search updated to version v0.19.1
• ragbits-evaluate updated to version v0.19.1
• ragbits-guardrails updated to version v0.19.1
• ragbits-core updated to version v0.19.1

v0.19.0

0.19.0 (2025-05-27)

Changed

• ragbits-chat updated to version v0.19.0
• ragbits-cli updated to version v0.19.0
• ragbits-document-search updated to version v0.19.0
• ragbits-evaluate updated to version v0.19.0
• ragbits-guardrails updated to version v0.19.0
• ragbits-core updated to version v0.19.0

v0.18.0

0.18.0 (2025-05-22)

Changed

• ragbits-chat updated to version v0.18.0
• ragbits-cli updated to version v0.18.0
• ragbits-document-search updated to version v0.18.0
• ragbits-evaluate updated to version v0.18.0
• ragbits-guardrails updated to version v0.18.0
• ragbits-core updated to version v0.18.0