This release adds the following new features, improvements and bug fixes.

Bug Fixes

• Update build script for macOS builds (#964)
• Additional checks for tar file extraction (#965)

🎉 We're excited to announce the release of txtai 9.0 🎉

If you like txtai, please remember to give it a ⭐!

9.0 adds first class support for sparse vector models (i.e. SPLADE), late interaction models (i.e. ColBERT), fixed dimensional encoding (i.e. MUVERA) and reranking pipelines.

There are also plenty of improvements and bug fixes!

New Features

• Add sparse vector scoring (#924)
• Add IVFFlat indexing for sparse vectors (#929)
• Add pgsparse scoring (#930)
• Add support for Inference-Free Splade (#934)
• Add support for late interaction models (#945, #954)
• Add ability to merge late interaction vectors into fixed dimensional MUVERA vectors (#952)
• Add Reranker pipeline (#960)
• Add what's new in txtai 9.0 notebook (#956)
• Add example notebook for Medical RAG Research with txtai (#921)

Improvements

• Add parameter to strip thinking tags from LLM outputs (#920)
• Update default Embeddings parameters (#925)
• Update sentence transformers pool call to use v5.0 features (#927)
• Improve hybrid scoring algorithm (#931)
• Pass kwargs to msgpack serializer (#932)
• Refactor ANN and Vectors packages into sparse + dense (#935)
• Refactor dense-only calls to accept sparse data (#936)
• Add checkpoint recovery to scoring and subindexes (#937)
• Modify pgvector ann index to build after data load (#938)
• Limit pgsparse input vectors to 1000 non-zero elements (#939)
• Change default sparse vector model (#940)
• Require sparse keyword/vector scores to be greater than 0 (#941)
• IVFSparse Improvements (#943)
• Change sparse vector normalization logic (#946)
• Change default behavior for pickle serialization (#949)
• Update similarity pipeline to support late interaction models (#953)
• Update benchmark scripts to support Similarity pipeline (#955)
• Update benchmarks script to support similarity and reranking pipelines (#961)

Bug Fixes

• Remove onnxxmltools workaround (#916)
• Textractor extracting text twice in versions >8.5.0 (#919)
• Update test to workaround HF Hub HTTP 429 issues (#926)
• Workaround issue with latest version of llama-cpp-python (#928)
• Ensure scores returned from scoring module are floats and not NumPy values (#933)
• Modify LiteLLM path detection logic (#947)
• Add build script workaround for LiteLLM issue (#957)
• Workaround build issue with latest version of Chonkie (#962)
• Update tests with exponential http backoff to work around constant HF Hub 429 errors (#963)

This release fixes a number of integration issues with downstream libraries and other performance improvements.

See below for full details on the new features, improvements and bug fixes.

Improvements

• Handling truncation for the Similarity pipeline (#882)
• Update tagline to the all-in-one AI framework (#901)

Bug Fixes

• Encoding issue with latest version of LiteLLM (#902)
• Fix bug with latest version of smolagents (#906)
• Import error with latest version of onnx (#907)
• Upcoming breaking GrandCypher API change (#909)
• Max Length parameter is ignored in LLM and Summary pipelines with latest version of Transformers (#912)
• Fix issue with latest version of smolagents (#913)

This release migrates from Transformers Agents to smolagents, adds Model Context Protocol (MCP) support and now requires Python 3.10+

See below for full details on the new features, improvements and bug fixes.

New Features

• Migrate to smolagents (#890)
• Add Model Context Protocol (MCP) Support (#892)
• Add support for MCP servers to Agent Framework (#898)
• Require Python 3.10 (#897)

Improvements

• Lazy load list of translation models (#896)

Bug Fixes

• Fix issue with MessageRole Enums and LLM pipeline (#888)
• Transformers 4.50 modified cached_file behavior (#889)
• Add test vision model compatible with Transformers 4.50 (#891)
• Fix bug introduced with Pillow 11.2 (#895)

This release adds support for vision LLMs, graph vector search, embeddings checkpoints, observability and an OpenAI-compatible API

See below for full details on the new features, improvements and bug fixes.

New Features

• Add support for vision models to HF LLM pipeline (#884)
• Add similar query clause to graph queries (#875)
• Feature Request: Embeddings index checkpointing (#695)
• Feature Request: Enhance observability and tracing capabilities (#869)
• Add OpenAI API compatible endpoint to API (#883)
• Add example notebook showing how to use OpenAI compatible API (#887)
• Add texttospeech pipeline to API (#552)
• Add upload endpoint to API (#659)

Improvements

• Add encoding parameter to TextToSpeech pipeline (#885)
• Add support for input streams to Transcription pipeline (#886)

Bug Fixes

• Fix bug with latest version of Transformers and model registry (#878)

This release adds the following new features, improvements and bug fixes.

Bug Fixes

• Ensure staticvectors is installed before calling method (#876)

This release adds support for GLiNER, Chonkie, Kokoro TTS and Static Vectors

See below for full details on the new features, improvements and bug fixes.

New Features

• Add support for GLiNER models (#862) Thank you @urchade
• Add semantic chunking pipeline (#812) Thank you @bhavnicksm
• Add Kokoro TTS support to TextToSpeech pipeline (#854) Thank you @hexgrad
• Add staticvectors inference (#859)
• Add example notebook for Entity Extraction with GLiNER (#873)
• Add example notebook for RAG Chunking (#874)
• Add notebook that analyzes NeuML LinkedIn posts (#851)

Improvements

• Add new methods for audio signal processing (#855)
• Remove fasttext dependency (#857)
• Remove WordVectors.build method (#858)
• Detect graph queries and route to graph index (#865)
• Replace python-louvain library with networkx equivalent (#867)
• Word vector model improvements (#868)
• Improve parsing of table text in HTML to Markdown pipeline (#872)

Bug Fixes

• Update build script to workaround breaking change with latest version of Transformers and Python 3.9 (#852)
• Incorrect Endpoint Description in Swagger UI (FastAPI) (#860)
• Handle empty token list with word vectorization (#861)

This release simplifies LLM chat messages, adds attribute filtering to Graph RAG and enables multi-cpu/gpu vector encoding

See below for full details on the new features, improvements and bug fixes.

New Features

• Add defaultrole to LLM pipeline (#841)
• Feature Request: Graph RAG - Add extra attributes (#684)
• Support graph=True in embeddings config (#848)
• Support pulling attribute data in graph.scan (#849)
• Encoding using multiple-GPUs (#541)
• Add vectors argument to Model2Vec vectors (#846)
• Enhanced Docs: LLM Embedding Examples (#843, #844) Thank you @igorlima!

Improvements

• Pin build script to pillow==10.4.0 (#800)
• Ensure generated datetimes are in UTC (#840)
• Update RAG notebooks to add clarifying notes on LLM inference (#847)

This release adds Docling integration, Embeddings context managers and significant database component enhancements

See below for full details on the new features, improvements and bug fixes.

New Features

• Add text extraction with Docling (#814)
• Add Embeddings context manager (#832)
• Add support for halfvec and bit vector types with PGVector ANN (#839)
• Persist embeddings components to specified schema (#829)
• Add example notebook that analyzes the Hugging Face Posts dataset (#817)
• Add an example notebook for autonomous agents (#820)

Improvements

• Cloud storage improvements (#821)
• Autodetect Model2Vec model paths (#822)
• Add parameter to disable text cleaning in Segmentation pipeline (#823)
• Refactor vectors package (#826)
• Refactor Textractor pipeline into multiple pipelines (#828)
• RDBMS graph.delete tests and upgrade graph dependency (#837)
• Bound ANN hamming scores between 0.0 and 1.0 (#838)

Bug Fixes

• Fix error with inferring function parameters in agents (#816)
• Add programmatic workaround for Faiss + macOS (#818) Thank you @yukiman76!
• docs: update 49_External_database_integration.ipynb (#819) Thank you @eltociear!
• Fix memory issue with llama.cpp LLM pipeline (#824)
• Fix issue with calling cached_file for local directories (#825)
• Fix resource issues with embeddings indexing components backed by databases (#831)
• Fix bug with NetworkX.hasedge method (#834)

🎉 We're excited to announce the release of txtai 8.0 🎉

If you like txtai, please remember to give it a ⭐!

8.0 introduces agents. Agents automatically create workflows to answer multi-faceted user requests. Agents iteratively prompt and/or interface with tools to step through a process and ultimately come to an answer for a request.

This release also adds support for Model2Vec vectorization. See below for more.

New Features

• Add txtai agents 🚀 (#804)
• Add agents package to txtai (#808)
• Add documentation for txtai agents (#809)
• Add agents to Application and API interfaces (#810)
• Add what's new in txtai 8.0 notebook (#811)
• Add model2vec vectorization (#801)

Improvements

• Update BASE_IMAGE in Dockerfile (#799)
• Cleanup vectors package (#802)
• Build script improvements (#805)

Bug Fixes

• ImportError: cannot import name 'DuckDuckGoSearchTool' from 'transformers.agents' (#807)