You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: CHANGELOG.md
+73-2
Original file line number
Diff line number
Diff line change
@@ -5,6 +5,77 @@ All notable changes to this project will be documented in this file.
5
5
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
6
6
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7
7
8
+
## [7.1.0] - 2024-06-10
9
+
10
+
### Added
11
+
12
+
- Add new Vector Store endpoints - thanks to [@willywg](https://github.com/willywg) for this PR!
13
+
- Add parameters to batches.list endpoint so you can for example use `after` - thanks to [@marckohlbrugge](https://github.com/marckohlbrugge)!
14
+
- Add vision as permitted purpose for files - thanks again to [@willywg](https://github.com/willywg) for the PR.
15
+
- Add improved README example of tool calling - thanks [@krschacht](https://github.com/krschacht) - check out his project [HostedGPT](https://github.com/AllYourBot/hostedgpt)!
16
+
17
+
### Fixed
18
+
19
+
- Fix broken link in README table of contents - thanks to [@garrettgsb](https://github.com/garrettgsb)!
20
+
- Skip sending nil headers - thanks to [@drnic](https://github.com/drnic)!
21
+
22
+
## [7.0.1] - 2024-04-30
23
+
24
+
### Fixed
25
+
26
+
- Update to v2 of Assistants in Messages, Runs, RunSteps and Threads - thanks to [@willywg](https://github.com/willywg) and others for pointing this out.
27
+
28
+
## [7.0.0] - 2024-04-27
29
+
30
+
### Added
31
+
32
+
- Add support for Batches, thanks to [@simonx1](https://github.com/simonx1) for the PR!
33
+
- Allow use of local LLMs like Ollama! Thanks to [@ThomasSevestre](https://github.com/ThomasSevestre)
34
+
- Update to v2 of the Assistants beta & add documentation on streaming from an Assistant.
35
+
- Add Assistants endpoint to create and run a thread in one go, thank you [@quocphien90](https://github.com/
36
+
quocphien90)
37
+
- Add missing parameters (order, limit, etc) to Runs, RunSteps and Messages - thanks to [@shalecraig](https://github.com/shalecraig) and [@coezbek](https://github.com/coezbek)
- Add Messages#modify to README - thanks to [@nas887](https://github.com/nas887)
40
+
- Don't add the api_version (`/v1/`) to base_uris that already include it - thanks to [@kaiwren](https://github.com/kaiwren) for raising this issue
41
+
- Allow passing a `StringIO` to Files#upload - thanks again to [@simonx1](https://github.com/simonx1)
42
+
- Add Ruby 3.3 to CI
43
+
44
+
### Security
45
+
46
+
-[BREAKING] ruby-openai will no longer log out API errors by default - you can reenable by passing `log_errors: true` to your client. This will help to prevent leaking secrets to logs. Thanks to [@lalunamel](https://github.com/lalunamel) for this PR.
47
+
48
+
### Removed
49
+
50
+
-[BREAKING] Remove deprecated edits endpoint.
51
+
52
+
### Fixed
53
+
54
+
- Fix README DALL·E 3 error - thanks to [@clayton](https://github.com/clayton)
55
+
- Fix README tool_calls error and add missing tool_choice info - thanks to [@Jbrito6492](https://github.com/Jbrito6492)
56
+
57
+
## [6.5.0] - 2024-03-31
58
+
59
+
### Added
60
+
61
+
- Add back the deprecated Completions endpoint that I removed a bit prematurely. Thanks, [@mishranant](https://github.com/
62
+
mishranant) and everyone who requested this.
63
+
64
+
## [6.4.0] - 2024-03-27
65
+
66
+
### Added
67
+
68
+
- Add DALL·E 3 to specs and README - thanks to [@Gary-H9](https://github.com/Gary-H9)
69
+
- Add Whisper transcription language selection parameter to README - thanks to [@nfedyashev](https://github.com/nfedyashev)
70
+
- Add bundle exec rake lint and bundle exec rake test to make development easier - thanks to [@ignacio-chiazzo](https://github.com/ignacio-chiazzo)
71
+
- Add link to [https://github.com/sponsors/alexrudall](https://github.com/sponsors/alexrudall) when users run `bundle fund`
72
+
73
+
### Fixed
74
+
75
+
- Update README and spec to use tool calls instead of functions - thanks to [@mpallenjr](https://github.com/mpallenjr)
76
+
- Remove nonexistent Thread#list method - thanks again! to [@ignacio-chiazzo](https://github.com/ignacio-chiazzo)
77
+
- Update finetunes docs in README to use chat instead of completions endpoint - thanks to [@blefev](https://github.com/blefev)
78
+
8
79
## [6.3.1] - 2023-12-04
9
80
10
81
### Fixed
@@ -45,13 +116,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
45
116
-[BREAKING] Switch from legacy Finetunes to the new Fine-tune-jobs endpoints. Implemented by [@lancecarlson](https://github.com/lancecarlson)
46
117
-[BREAKING] Remove deprecated Completions endpoints - use Chat instead.
47
118
48
-
### Fix
119
+
### Fixed
49
120
50
121
-[BREAKING] Fix issue where :stream parameters were replaced by a boolean in the client application. Thanks to [@martinjaimem](https://github.com/martinjaimem), [@vickymadrid03](https://github.com/vickymadrid03) and [@nicastelo](https://github.com/nicastelo) for spotting and fixing this issue.
51
122
52
123
## [5.2.0] - 2023-10-30
53
124
54
-
### Fix
125
+
### Fixed
55
126
56
127
- Added more spec-compliant SSE parsing: see here https://html.spec.whatwg.org/multipage/server-sent-events.html#event-stream-interpretation
57
128
- Fixes issue where OpenAI or an intermediary returns only partial JSON per chunk of streamed data
0 commit comments