Releases: timescale/pgai
pgai: v0.3.0
0.3.0 (2024-12-10)
⚠ BREAKING CHANGES
- remove
truncate
parameter from Ollama/Voyage APIs (#284)
Features
- add Voyage AI vectorizer integration (#256) (1b56d62)
- remove
truncate
parameter from Ollama/Voyage APIs (#284) (ecda03c) - add
load_dataset
function for creating a table from a HuggingFace dataset (#253)(2946938)
Bug Fixes
extension-0.6.0
This release adds support for using Voyage AI in a vectorizer, and loading
datasets from hugging face.
New features and improvements
- Use the
ai.voyageai_embed
, andai.embedding_voyageai
functions to use Voyage AI for vector embeddings 1b56d62. - Add
ai.load_dataset
to load datasets from hugging face 2946938. - Change the type of
keep_alive
parameter fromfloat8
totext
0c74741 - Remove
truncate
parameter from Ollama/Voyage APIs ecda03c
Fixes
- Fix Anthropic tool use 2cb2fe9.
Full Changelog: extension-0.5.0...extension-0.6.0
pgai: v0.2.1
pgai: v0.2.0
0.2.0 (2024-11-26)
Features
- add Ollama support to vectorizer (6a4a449)
Bug Fixes
- make vectorizer worker poll for new vectorizers (0672e7a)
Miscellaneous
- a new database for each test (4ed938b)
- add logo to pgai pypi (3366368)
- add test for recursive text splitting (#207) (4a35fc6)
- migrate project commands from Make to Just (42a8f79)
- migrate to uv and hatch (#188) (627cf33)
- refactor test infra (ac845ca)
- run pgai tests against extension from source (ffc20d2)
- scope postgres_container fixture to class (12c1780)
- separate the dev/test/build between the projects (183be9e)
- test the cli instead of the lambda handler (#204) (3a48f82)
extension-0.5.0
This release adds support for Ollama-based vectorizers, and fixes a permissions issue introduced in 0.4.1.
For more details, see the release notes.
extension 0.4.1
This release focuses on improving reliability, performance, and maintainability while fixing several important edge cases in table management and permissions.
For more details, see the release notes.
extension 0.4.0
Version 0.4.0 adds support for pgai Vectorizer, a new tool for automatically creating and updating vector embeddings for data in PostgreSQL.
This release adds extension capabilities to support using pgai Vectorizer self-hosted or managed via the Timescale Cloud platform.
For more details, see the release notes.
v0.3.0
Version 0.3.0 adds support for Anthropic and Cohere.
The following functions were added:
- anthropic_generate
- cohere_chat_complete
- cohere_classify_simple
- cohere_classify
- cohere_detokenize
- cohere_embed
- cohere_list_models
- cohere_rerank_simple
- cohere_rerank
- cohere_tokenize