Releases: docqai/docq
Releases · docqai/docq
v0.13.8
fix(API): error handling to not cover 404 with a 500
Full Changelog: v0.13.7...v0.13.8
v0.13.7
Full Changelog: v0.13.6...v0.13.7
v0.13.6
Full Changelog: v0.13.5...v0.13.6
v0.13.5
build: bump version
v0.13.4
Full Changelog: v0.13.2...v0.13.4
v0.13.2
Full Changelog: v0.13.1...v0.13.2
v0.13.1
Contributors
janaka
Assets 2
v0.12.0
Contributors
janaka
Assets 2
v0.11.0
What's Changed
🏕 What's New
- fix: code chat history breaking chat
{is present by @janaka in #255 - Slack improvements 3 by @janaka in #258
- refactor: switch shared to use a Llama Index pipeline implementation and adopt HyDE. by @janaka in #259
- refactor: fix some undefined type errors
- build: update to Ruff v0.2.2 -> v0.4.4
- build: update llama-index-core
- refactor: split things into files a bit more to avoid circular deps.
- docs(readme): update 2nd level tag line to make it clearer.
- tests: fix failing test from moving some indexing and storage functions to a different file.
- feat: add GPT-4o support
- refactor: move azure env var strings to config file and reference by py variable in code
- update azure_openai_latest setting to use gpt-4o
Full Changelog: v0.10.6...v0.11.0
Contributors
janaka
Assets 2
v0.10.6
fix: code chat history breaking chat { is present (#255)
- fix: escape { and } in message history before sending to retrieval class
- otherwise it breaks because we are using the message template feature as a hack to get message history into the LLM call messages collection.
- chore: fix typo in copy
- fix: handle org setting enabled feat keys that are no longer valid. That's a feature that used to exist that was saved as a setting for an org in the DB. When the feature is removed from the avail features list (enum) because we no longer want it, we want the admin UI code to just ignore it.
Full Changelog: v0.10.6...v0.10.6