doc: openAIChat #63
Closed
doc: openAIChat #63
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Refactor `messageHistory` to be agnostic of the image encoding. * Add backend encoding of images to `openAIChat`, `azureChat`, and `ollamaChat`. * Add image test points to the test files. Open question: Can we reliably detect which Ollama models support vision?
Preinstall bakllava, to have a vision model
Co-authored-by: MiriamScharnke <[email protected]>
Co-authored-by: Christopher Creutzig <[email protected]>
Co-authored-by: Christopher Creutzig <[email protected]>
Generating Markdown in pre-commit hook. The hook needs to be activated in the local repository, by including it in `.git/hooks/pre-commit`.
Co-authored-by: MiriamScharnke <[email protected]>
Future versions will get that automatically, from commit 570aaa1.
…g/llms-with-matlab into generate-md-from-mlx
Ollama images
MiriamScharnke
changed the title
ccreutzi
requested changes
Jul 29, 2024
There was a problem hiding this comment.
I wish I could mark individual comments as “request change” or “just an aside, feel free to ignore.”
I think the only thing where I have a flag is the Tools documentation. Let me know if the functionality there is completely opaque – we didn't come up with the terminology.
Co-authored-by: Christopher Creutzig <[email protected]>
I know why those happened, and can avoid them in the future! In MLX files, you can create hyperlinks which link to lines in the same file. I tried to see whether this would translate into the markdown - turns out it hasn't. What it has done is taken those hyperlinks and just given them extra backticks with no functionality. So long as I stop trying to link between passages, this should not be an issue. Co-authored-by: Christopher Creutzig <[email protected]>
Co-authored-by: Christopher Creutzig <[email protected]>
ccreutzi
reviewed
Jul 30, 2024
Moved mlx into sub-directory, added Markdown export
Co-authored-by: Deborah Ferreira <[email protected]>
Co-authored-by: Christopher Creutzig <[email protected]>
This file was not meant for this change.
Fix openai trademark
ccreutzi
approved these changes
Aug 1, 2024
| Instead of using the `APIKey` name\-value argument, you can also set the environment variable OPEN\_API\_KEY. For more information, see [https://github.com/matlab\-deep\-learning/llms\-with\-matlab/blob/main/doc/OpenAI.md](https://github.com/matlab-deep-learning/llms-with-matlab/blob/main/doc/OpenAI.md). | ||
| Instead of using the `APIKey` name\-value argument, you can also set the environment variable OPEN\_API\_KEY. For more information, see [OpenAI API](../OpenAI.md). | ||
|
|
||
| --- |
There was a problem hiding this comment.
These lines look heavier in the preview than the section break for “Properties Settable at Construction” below.
doc/functions/openAIChat.md
Outdated
Comment on lines
280
to
245
| generate(chat,"Why is a raven like a writing desk?") | ||
| generate(chat,"Why is a raven like a writing desk?"); |
There was a problem hiding this comment.
Generating text and discarding the output without saving it anywhere seems a bit pointless. Can we remove the semicolon?
There was a problem hiding this comment.
We can; do you want me to actually generate some text and also print the output?
There was a problem hiding this comment.
Possibly? Maybe faked or with an elision, so it doesn't get too long?
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## documentation #63 +/- ##
=================================================
- Coverage 97.13% 97.11% -0.03%
=================================================
Files 39 41 +2
Lines 1292 1350 +58
=================================================
+ Hits 1255 1311 +56
- Misses 37 39 +2 ☔ View full report in Codecov by Sentry. |
…nces Allow (long) char vectors for StopSequences
moondream is a much smaller vision model and perfectly suitable for the tests we want to run.
Replace bakllava by moondream
Create CODEOWNERS
To decouple `texampleTests.m` from availability and speed of external servers, record calls to `llms.internal.sendRequest` (on dev machine) and replay (during most test runs, including CI). See tests/recording/README.md for instructions.
The streaming interface sometimes responds with something like `json.choices = {"index":0,"delta":{},"logprobs":[],"finish_reason":"length"}`. Stop blindly assuming `json.choices.delta.content` exists.
Avoid bogus access to `json.choices.delta.content`
Trace/replay `llms.internal.sendRequest`
Co-authored-by: Christopher Creutzig <[email protected]>
…-with-matlab into doc-openaichat
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Create functions directory in the doc folder and add openAIChat documentation.