Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Release 0.7.0 #38

Merged
merged 2 commits into from
Apr 28, 2024
Merged

Release 0.7.0 #38

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d0b16d2
Release 0.7.0
github-actions[bot] Apr 28, 2024
3dff13e
Update HISTORY.md
extremeheat Apr 28, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 29 additions & 1 deletion HISTORY.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,32 @@
### 0.6.1
## 0.7.0
### Breaking
* Remove old "guidance regions"
* Flow arguments for prompt handling have been updated.
* `prompt: string` replaced with `prompt: { system?: string, user?: string }` or `prompt: { text: string, roles: Record<string, Role> }` to support new role handling.

### Features
* Support "role" splitting in markdown processor. See docs/MarkdownProcessor.md's role section for doc.
* calling loadPrompt() now accepts a new arg, options, which can take an a "role" field, set to a Record<string, string> map. The keys are the tokens to split by and the values are the roles.
* Add "requestChatCompletion" API method on CompletionService for sending messages to models
* Supports caching
* Old "guidance regions" removed from `requestCompletion()` in favor of a new "guidance" role in messages which can be used now via "requestChatCompletion"
* Markdown processor now strips markdown comments out
* `content` and `text` are returned on all completion requests, whether chat or not
* Add a basic token counting bin script for counting GPT-4 tokens (`npx langxlang count gpt4 file.txt`)

### Fixes
* Fix caching issues in CompletionService for requestCompletion
* Fixes to markdown tokenization (handle comments, preformatted blocks)
* Fix Flow transformResponse

### Changelog
* [Bump @google/generative-ai from 0.7.1 to 0.8.0 (#36)](https://github.com/extremeheat/LXL/commit/b3169cde485c19e038aeb7e86b40cd0f6653c7ca) (thanks @dependabot[bot])
* [tools: Improvements to stripping and code collection, add a token counting bin script (#37)](https://github.com/extremeheat/LXL/commit/41d49fbe6849fb18bc538e24db09735a7fb81fd1) (thanks @extremeheat)
* [Add role splitting in markdown processor, remove old guidance regions (#34)](https://github.com/extremeheat/LXL/commit/f4840f6b2072975da01d8c332b10bfc6944c97ea) (thanks @extremeheat)
* [Support stop sequences, generation options in ChatSession, AIStudio improvements (#33)](https://github.com/extremeheat/LXL/commit/b72066f2f53b5c52bda39db71ea9cfd39b192e20) (thanks @extremeheat)
* [Update examples](https://github.com/extremeheat/LXL/commit/e290f43847ea1c2cbe1bf4dfaebdb8e236e26b09) (thanks @extremeheat)

## 0.6.1
* [Bump @google/generative-ai from 0.6.0 to 0.7.1 (#30)](https://github.com/extremeheat/LXL/commit/7e0389feac29fd6bb4505cd780166e6be65b1e91) (thanks @dependabot[bot])
* [Fix Gemini completions not emitting stop chunk](https://github.com/extremeheat/LXL/commit/f44f5641e58154dc6fb1cd3cfc45fb6da3e033a6) (thanks @extremeheat)

Expand Down
2 changes: 1 addition & 1 deletion package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "langxlang",
"version": "0.6.1",
"version": "0.7.0",
"description": "LLM wrapper for OpenAI GPT and Google Gemini and PaLM 2 models",
"main": "src/index.js",
"types": "src/index.d.ts",
Expand Down
Loading