π‘ All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
This release adds dynamic embeddings vector support along with semantic graph and RAG improvements
See below for full details on the new features, improvements and bug fixes.
If you like txtai, please remember to give it a β!
7.0 introduces the next generation of the semantic graph. This release adds support for graph search, advanced graph traversal and graph RAG. It also adds binary support to the API, index format improvements and training LoRA/QLoRA models. See below for more.
A big thank you goes to Jordan Matelsky (@j6k4m8) for his help in integrating the GrandCypher library into txtai!
This release adds new LLM inference methods, API Authorization and RAG improvements
π New LLM methods. llama.cpp and LiteLLM support added. LLM pipeline now supports Hugging Face models, GGUF files and LLM API inference all with one line of code.
π API Authorization. Adds support for API keys and pluggable authentication methods when running through txtai API.
See below for full details on the new features, improvements and bug fixes.
This release adds binary quantization, bind parameters for multimedia SQL queries and performance improvements
β‘ Scalar quantization. Supports 1 bit (binary) through 8 bit quantization. Can dramatically reduce vector storage requirements.
π SQL bind parameters. Enables searching binary content with SQL statements, along with being a standard best practice.
See below for full details on the new features, improvements and bug fixes.
This release adds metadata support for client-server databases and custom scoring implementations
ποΈ Client-server database integration. Store index metadata in Postgres, MariaDB/MySQL, MSSQL and more.
πΉ Custom scoring implementations. Store keyword index data in systems such as Elasticsearch. Similar to functionality already available in vector index component.
See below for full details on the new features, improvements and bug fixes.
This significant milestone release marks txtai's 3 year birthdayπ If you like txtai, please remember to give it a β!
6.0 adds sparse, hybrid and subindexes to the embeddings interface. It also makes significant improvements to the LLM pipeline workflow. See below for more.
Breaking changes
The vast majority of changes are fully backwards compatible. New features are only enabled when specified. The only breaking change is with the Scoring
terms interface, where the index format changed. The main Scoring
interface used for word vectors weighting is unchanged.
This release adds workflow streams and DuckDB as a database backend
βͺοΈοΈ Workflow streams enable server-side processing of large datasets. Streams iteratively pass content to workflows, no need to pass bulk data through the API.
π¦ DuckDB is a new database backend. Certain larger non-vector driven queries and aggregations will now run significantly faster than with SQLite.
See below for full details on the new features, improvements and bug fixes.
This release adds prompt templates, conversational task chaining and Hugging Face Hub integration
π Prompt templates dynamically generate text using workflow task inputs. This enables chaining multiple prompts and models together.
π€ Embeddings now integrate with the Hugging Face Hub! Easily share and load embeddings indexes. There is a full embeddings index available for English Wikipedia.
See below for full details on the new features, improvements and bug fixes.
This release adds embeddings-guided and prompt-driven search along with a number of methods to train language models
π Prompt-driven search is a big step forward towards conversational search in txtai. With this release, complex prompts can now be passed to txtai to customize how search results are returned. Lots of exciting possibilities on this front, stay tuned.
π‘ The trainer pipeline now has support for training language models from scratch. It supports masked language modeling (MLM), causal language modeling (CLM) and replaced token detection (ELECTRA-style). This is part of the micromodels effort.
See below for full details on the new features, improvements and bug fixes.