-
Notifications
You must be signed in to change notification settings - Fork 29
Permalink
Choose a base ref
{{ refName }}
default
Choose a head ref
{{ refName }}
default
Comparing changes
Choose two branches to see what’s changed or to start a new pull request.
If you need to, you can also or
learn more about diff comparisons.
Open a pull request
Create a new pull request by comparing changes across two branches. If you need to, you can also .
Learn more about diff comparisons here.
base repository: matlab-deep-learning/llms-with-matlab
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v4.0.0
Could not load branches
Nothing to show
Loading
Could not load tags
Nothing to show
{{ refName }}
default
Loading
...
head repository: matlab-deep-learning/llms-with-matlab
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: main
Could not load branches
Nothing to show
Loading
Could not load tags
Nothing to show
{{ refName }}
default
Loading
5
contributors
Commits on Oct 30, 2024
-
For some reason, we used both `OPENAI_KEY` and `OPENAI_API_KEY` env variables, expecting them to have the same values. Drop the `OPENAI_KEY` one, since we document our use of `OPENAI_API_KEY`.
Configuration menu - View commit details
-
Copy full SHA for e16afaf - Browse repository at this point
Copy the full SHA e16afafView commit details
Commits on Oct 31, 2024
-
This test point runs fine on multiple dev machines (with updated Ollama), but fails in CI with an internal error to Ollama/llama.cpp: ``` ================================================================================ Error occurred in tollamaChat/generateWithImages and it did not run to completion. --------- Error ID: --------- 'llms:apiReturnedError' -------------- Error Details: -------------- Error using ollamaChat/generate (line 238) Server returned error indicating: "an unknown error was encountered while running the model GGML_ASSERT(i01 >= 0 && i01 < ne01) failed" Error in tollamaChat>@(~)generate(chat,messages) (line 136) text = arrayfun(@(~) generate(chat,messages), 1:5, UniformOutput=false); Error in tollamaChat/generateWithImages (line 136) text = arrayfun(@(~) generate(chat,messages), 1:5, UniformOutput=false); ================================================================================ ``` See also ollama/ollama#7288
Configuration menu - View commit details
-
Copy full SHA for 353d807 - Browse repository at this point
Copy the full SHA 353d807View commit details
Commits on Nov 1, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 739b5a2 - Browse repository at this point
Copy the full SHA 739b5a2View commit details
Commits on Nov 4, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 5b3ac4e - Browse repository at this point
Copy the full SHA 5b3ac4eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 6eb862e - Browse repository at this point
Copy the full SHA 6eb862eView commit details -
Configuration menu - View commit details
-
Copy full SHA for b420b8b - Browse repository at this point
Copy the full SHA b420b8bView commit details -
Merge pull request #82 from matlab-deep-learning/removeCodeCov
Remove configuration for codecov
Configuration menu - View commit details
-
Copy full SHA for 3dfac40 - Browse repository at this point
Copy the full SHA 3dfac40View commit details
Commits on Nov 5, 2024
-
Using `dlarray` in a prototype results in `dlarray` in the output, but without the dimension labels. Reason: `cast(X,'like',Y)` behaves that way for `dlarray` `Y`. Given that we do not return higher-dimensional data anyway, it is questionable whether there is any reason one would want to allow `dlarray` in prototypes. Not handling them properly means we are better off disabling them altogether. Without a dependency on Deep Learning Toolbox, we cannot have an automated test point for this change, unfortunately.
Configuration menu - View commit details
-
Copy full SHA for e6199f3 - Browse repository at this point
Copy the full SHA e6199f3View commit details -
Merge pull request #83 from matlab-deep-learning/add-enrico
Add Enrico as code owner
Configuration menu - View commit details
-
Copy full SHA for 8d4ca80 - Browse repository at this point
Copy the full SHA 8d4ca80View commit details -
ToolChoice="none" for azureChat
`azureChat` should support `ToolChoice="none"`
Configuration menu - View commit details
-
Copy full SHA for c5e2ef1 - Browse repository at this point
Copy the full SHA c5e2ef1View commit details -
Return tool calls properly in azureChat
Make `azureChat` handle tool calls returned the same way we do in `openAIChat`.
Configuration menu - View commit details
-
Copy full SHA for 245e4b0 - Browse repository at this point
Copy the full SHA 245e4b0View commit details
Commits on Nov 13, 2024
-
Stop warning in constructor for
ResponseFormat="json"
Since we now throw an error when `ResponseFormat="json"` is used without the required `"json"` in the inputs, we can stop warning in the constructor. With the previous state, users got a warning they could not avoid, even in code doing everything correctly.
Configuration menu - View commit details
-
Copy full SHA for 2d0ec2d - Browse repository at this point
Copy the full SHA 2d0ec2dView commit details -
change example to using structured output
Configuration menu - View commit details
-
Copy full SHA for 3b1db9d - Browse repository at this point
Copy the full SHA 3b1db9dView commit details
Commits on Dec 13, 2024
-
* Activate structured output for ollamaChat * Update documentation
Configuration menu - View commit details
-
Copy full SHA for 44a3679 - Browse repository at this point
Copy the full SHA 44a3679View commit details -
Configuration menu - View commit details
-
Copy full SHA for b8bfd78 - Browse repository at this point
Copy the full SHA b8bfd78View commit details -
Configuration menu - View commit details
-
Copy full SHA for 25b8ffc - Browse repository at this point
Copy the full SHA 25b8ffcView commit details
Commits on Dec 18, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 70baea5 - Browse repository at this point
Copy the full SHA 70baea5View commit details -
runtests should not print unnecessary text to command window and test log
Configuration menu - View commit details
-
Copy full SHA for 3f312b5 - Browse repository at this point
Copy the full SHA 3f312b5View commit details
Commits on Jan 23, 2025
-
Configuration menu - View commit details
-
Copy full SHA for 11a54ea - Browse repository at this point
Copy the full SHA 11a54eaView commit details
Commits on Jan 30, 2025
-
Update list of supported models on OpenAI
Add o1, remove the deprecated 3.5-0613 models. Change examples from outdated 3.5-turbo models to newer ones (picked at random). `topenAIChat/canUseModel` needed a change because the o1 models error with `MaxNumTokens=1`, as they need a few tokens to get the multiple stages started.
Configuration menu - View commit details
-
Copy full SHA for 098c830 - Browse repository at this point
Copy the full SHA 098c830View commit details -
Support tool calling for
ollamaChat
* Switch from Mistral to Mistral NeMo Switch from Mistral to Mistral NeMo as the default model for tests and (tested) examples, to prepare for supporting function calls in `ollamaChat`. * Extract structured output tests * Activate structured output for ollamaChat * Improve error message when trying to use structured output with Ollama < 0.5.0 * extract tool call tests * tool support for Ollama * Adapt messageHistory to support Ollama specifics * response streamer should capture tool calls outside OpenAI's format * add Ollama function calling example to texampleTests * Minimal documentation updates * Split llms:assistantMustHaveTextNameAndArguments in two To make the error messages simpler
Configuration menu - View commit details
-
Copy full SHA for b5121ec - Browse repository at this point
Copy the full SHA b5121ecView commit details
Commits on Feb 3, 2025
-
Configuration menu - View commit details
-
Copy full SHA for 1c9e534 - Browse repository at this point
Copy the full SHA 1c9e534View commit details
Commits on Feb 7, 2025
-
Configuration menu - View commit details
-
Copy full SHA for ef2f01a - Browse repository at this point
Copy the full SHA ef2f01aView commit details -
Change models used in Ollama.md
Changed phi-3 to mistral, and llava to moondream.
Configuration menu - View commit details
-
Copy full SHA for b9e542a - Browse repository at this point
Copy the full SHA b9e542aView commit details
Commits on Feb 10, 2025
-
Add an additionally needed “requires Text Analytics Toolbox” for one of the examples which uses `tokenizedDocument`.
Configuration menu - View commit details
-
Copy full SHA for fb8b1d9 - Browse repository at this point
Copy the full SHA fb8b1d9View commit details
Commits on Feb 20, 2025
-
Configuration menu - View commit details
-
Copy full SHA for f42a4f0 - Browse repository at this point
Copy the full SHA f42a4f0View commit details
Commits on Feb 26, 2025
-
Refactor for readability
Configuration menu - View commit details
-
Copy full SHA for cbe5061 - Browse repository at this point
Copy the full SHA cbe5061View commit details
Commits on Mar 3, 2025
-
Refactoring of Ollama.md
Configuration menu - View commit details
-
Copy full SHA for b258ead - Browse repository at this point
Copy the full SHA b258eadView commit details -
Configuration menu - View commit details
-
Copy full SHA for a6a1e8f - Browse repository at this point
Copy the full SHA a6a1e8fView commit details
There are no files selected for viewing