multica Releases

Updated the web interface to a stable and simple version by removing unused components.

Jul 30, 2025

Updated the services component to a stable and simple version by removing unused components.

Jul 30, 2025

Enhanced data handling capabilities and configuration options for the project, including support for new file formats and environment variables.

Jul 14, 2025

Enhanced translation service capabilities with GiteeAI integration, new configuration options, and visual processing improvements.

Jul 4, 2025

Adds support for Replicate chat models, OpenAI o1 model, and Gemini 2.0 Flash. Enhances response handling and adds support for Redis Sentinel and Redis Cluster. Fixes balance queries for SiliconFlow and removes duplicate model names.

Feb 2, 2025

Adds support for Novita AI as a generator and includes basic tests for the Document class. It also fixes spaCy language issues and implements dynamic model name retrieval for the OpenAI Generator.

Jan 27, 2025

This release introduces a beta Evaluation tool for assessing Chat Engine performance, adds support for new LLM providers like Gitee AI, vLLM, and Xinference, and expands embedding model support with Gitee AI and Amazon Bedrock. It also includes improvements for file upload size limits and reference file downloads.

Jan 3, 2025

Adds SiliconFlow support and updates the Ollama embedding API to support multi-text embedding. Introduces Max Tokens and Context Window settings for Ollama, synchronizes with Groq models, and adds support for Claude Sonnet 3.5 v2, xAI, and OIDC.

Dec 22, 2024

This release adds support for Upstage (Reader, Embedder, Generator), Groq, and AssemblyAI. It introduces a new Custom deployment type, language detection for multiple languages, and improved Markdown Chunking. It also fixes various bugs related to environment variables, Ollama URL parsing, and client creation.

Dec 10, 2024

A major version update introducing async ingestion with realtime logging, migration to Weaviate v4 Client, and a completely reworked Admin Interface and Suggestion logic. It features advanced chunking strategies (Semantic, Recursive, HTML), a new Document Explorer, and support for VoyageAI and custom metadata.

Sep 6, 2024

Minimal release notes: "- [Release note](https://tidb.ai/docs/releases/v0.2.0) - [Deployment guide](https://tidb.ai/docs/deploy-with-docker) -"

Aug 22, 2024

Minimal release notes: "See [release note](https://tidb.ai/docs/releases/v0.1.0) and [deployment guide](https://tidb.ai/docs/deploy-with-docker)"

Aug 12, 2024

Adds support for Spark4.0 Ultra, Claude Sonnet 3.5, and Claude 3 tool use. Introduces Novita AI, Cloudflare OpenAI API support, and SMTP without authentication. Fixes Claude 4v text parameter issues and adds Proxy channel type.

Aug 6, 2024

Adds a cancel generation button, .docx file support, and a GitLab Reader. It improves HuggingFace embedding models and introduces MixedBreadEmbedder and AllMPNetEmbedder. Various bugs related to Ollama error logging and chunk NoneType checks are fixed.

Jul 2, 2024

This release adds support for GPT-4o and introduces new AI providers like Gemini embeddings, ByteDance Doubao, and Tencent V3 API. It also includes theme updates and fixes for various bugs related to token encoding, streaming, and function calls.

Jun 25, 2024

This release introduces support for several new AI providers, including AWS Bedrock, Groq, Cohere, and Ollama, while enhancing existing integrations like Gemini and Claude with streaming capabilities and tools support.

May 27, 2024