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.

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

fix: tool calling cohere #3355

Merged

Conversation

Anirudh31415926535
Copy link
Contributor

Why are these changes needed?

The tool calling in the current integration with Cohere has some subtle fallacies in them. These changes ensure that the tool calling happens in the apt mechanism for the Cohere models.

Checks

@Anirudh31415926535 Anirudh31415926535 changed the title fix: Tool calling cohere fix: tool calling cohere Aug 15, 2024
@Hk669 Hk669 requested review from marklysze and Hk669 August 15, 2024 16:09
@marklysze marklysze added the models Pertains to using alternate, non-GPT, models (e.g., local models, llama, etc.) label Aug 15, 2024
@marklysze
Copy link
Collaborator

Hi @Anirudh31415926535, thanks for your contribution - can you provide a code example that isn't working with the current code so we can test it?

@Anirudh31415926535
Copy link
Contributor Author

Anirudh31415926535 commented Aug 16, 2024

Hi @Anirudh31415926535, thanks for your contribution - can you provide a code example that isn't working with the current code so we can test it?

Hi @marklysze Thanks for looking through! I think its not so much that an example doesn't work because it throws an error...
Without these changes, the raw prompts that the Cohere model views is somewhat incomplete, which may impact performance.
Hope that clarifies! :)

@marklysze
Copy link
Collaborator

Hi @Anirudh31415926535, thanks for your contribution - can you provide a code example that isn't working with the current code so we can test it?

Hi @marklysze Thanks for looking through! I think its not so much that an example doesn't work because it throws an error... Without these changes, the raw prompts that the Cohere model views is somewhat incomplete, which may impact performance. Hope that clarifies! :)

Hey @Anirudh31415926535, thanks for the note - I'll give it a test. Would you be able to provide a little bit of a summary as to what may have been incomplete?

autogen/oai/cohere.py Outdated Show resolved Hide resolved
autogen/oai/cohere.py Outdated Show resolved Hide resolved
@Anirudh31415926535
Copy link
Contributor Author

Anirudh31415926535 commented Aug 23, 2024

Hi @Anirudh31415926535, thanks for your contribution - can you provide a code example that isn't working with the current code so we can test it?

Hi @marklysze Thanks for looking through! I think its not so much that an example doesn't work because it throws an error... Without these changes, the raw prompts that the Cohere model views is somewhat incomplete, which may impact performance. Hope that clarifies! :)

Hey @Anirudh31415926535, thanks for the note - I'll give it a test. Would you be able to provide a little bit of a summary as to what may have been incomplete?

Well, the basic idea is that from our api, we parse the different bits of the request body and have it formatted into a raw prompt that is seen by the model. Since the autogen integration was missing some parameters, it results in an incorrect/incomplete raw prompt being generated which is sent to our model, which might cause some regressions.

An example of this is that we need the tool_calls field in the chat history Chatbot messages, that is parsed and contributes to a section of the raw prompt that enabels the model to know that so and so tool call was performed as part of this conversation so that it can continue to hold context of it. If this were absent, then it would lead to that part of the raw prompt being empty, which would be unfortunate.
So, you wouldn't necessarily get an error, but since the raw prompts would be inaccurate, there might be some performance regressions.

Similarly, for the other changes added too! Hope that is a clearer picture of what I was referring to!

autogen/oai/cohere.py Outdated Show resolved Hide resolved
@marklysze
Copy link
Collaborator

marklysze commented Aug 23, 2024

Hey @Anirudh31415926535, thanks for the note - I'll give it a test. Would you be able to provide a little bit of a summary as to what may have been incomplete?

Well, the basic idea is that from our api, we parse the different bits of the request body and have it formatted into a raw prompt that is seen by the model. Since the autogen integration was missing some parameters, it results in an incorrect/incomplete raw prompt being generated which is sent to our model, which might cause some regressions.

An example of this is that we need the tool_calls field in the chat history Chatbot messages, that is parsed and contributes to a section of the raw prompt that enabels the model to know that so and so tool call was performed as part of this conversation so that it can continue to hold context of it. If this were absent, then it would lead to that part of the raw prompt being empty, which would be unfortunate. So, you wouldn't necessarily get an error, but since the raw prompts would be inaccurate, there might be some performance regressions.

Similarly, for the other changes added too! Hope that is a clearer picture of what I was referring to!

That's a great explanation and definitely a worthy change to incorporate :)

Thanks for coming and helping align AutoGen's client class with your API.

@marklysze
Copy link
Collaborator

@Anirudh31415926535, is it possible to move the code for the client_name down to the create function and use the params parameter which will have it. The reason is the init function only includes kwargs that align with OpenAI, so although it's in our config it won't come into the init. It will be passed into the create function.

It would also be good to update the documentation, I think just the "API parameters" section is okay:
/home/autogen/autogen/website/docs/topics/non-openai-models/cloud-cohere.ipynb

@Anirudh31415926535
Copy link
Contributor Author

@Anirudh31415926535, is it possible to move the code for the client_name down to the create function and use the params parameter which will have it. The reason is the init function only includes kwargs that align with OpenAI, so although it's in our config it won't come into the init. It will be passed into the create function.

It would also be good to update the documentation, I think just the "API parameters" section is okay: /home/autogen/autogen/website/docs/topics/non-openai-models/cloud-cohere.ipynb

Done! Just pushed the fixes!

Copy link
Collaborator

@marklysze marklysze left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@Anirudh31415926535 has been great in making all the adjustments - changes look good to go. Happy to merge!

@thinkall is that something you can help with?

@Anirudh31415926535
Copy link
Contributor Author

@Anirudh31415926535 please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.

@microsoft-github-policy-service agree [company="{your company}"]

Options:

  • (default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
  • (when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"

Contributor License Agreement

Contribution License Agreement

This Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”), and conveys certain license rights to Microsoft Corporation and its affiliates (“Microsoft”) for Your contributions to Microsoft open source projects. This Agreement is effective as of the latest signature date below.

  1. Definitions.
    “Code” means the computer software code, whether in human-readable or machine-executable form,
    that is delivered by You to Microsoft under this Agreement.
    “Project” means any of the projects owned or managed by Microsoft and offered under a license
    approved by the Open Source Initiative (www.opensource.org).
    “Submit” is the act of uploading, submitting, transmitting, or distributing code or other content to any
    Project, including but not limited to communication on electronic mailing lists, source code control
    systems, and issue tracking systems that are managed by, or on behalf of, the Project for the purpose of
    discussing and improving that Project, but excluding communication that is conspicuously marked or
    otherwise designated in writing by You as “Not a Submission.”
    “Submission” means the Code and any other copyrightable material Submitted by You, including any
    associated comments and documentation.
  2. Your Submission. You must agree to the terms of this Agreement before making a Submission to any
    Project. This Agreement covers any and all Submissions that You, now or in the future (except as
    described in Section 4 below), Submit to any Project.
  3. Originality of Work. You represent that each of Your Submissions is entirely Your original work.
    Should You wish to Submit materials that are not Your original work, You may Submit them separately
    to the Project if You (a) retain all copyright and license information that was in the materials as You
    received them, (b) in the description accompanying Your Submission, include the phrase “Submission
    containing materials of a third party:” followed by the names of the third party and any licenses or other
    restrictions of which You are aware, and (c) follow any other instructions in the Project’s written
    guidelines concerning Submissions.
  4. Your Employer. References to “employer” in this Agreement include Your employer or anyone else
    for whom You are acting in making Your Submission, e.g. as a contractor, vendor, or agent. If Your
    Submission is made in the course of Your work for an employer or Your employer has intellectual
    property rights in Your Submission by contract or applicable law, You must secure permission from Your
    employer to make the Submission before signing this Agreement. In that case, the term “You” in this
    Agreement will refer to You and the employer collectively. If You change employers in the future and
    desire to Submit additional Submissions for the new employer, then You agree to sign a new Agreement
    and secure permission from the new employer before Submitting those Submissions.
  5. Licenses.
  • Copyright License. You grant Microsoft, and those who receive the Submission directly or
    indirectly from Microsoft, a perpetual, worldwide, non-exclusive, royalty-free, irrevocable license in the
    Submission to reproduce, prepare derivative works of, publicly display, publicly perform, and distribute
    the Submission and such derivative works, and to sublicense any or all of the foregoing rights to third
    parties.
  • Patent License. You grant Microsoft, and those who receive the Submission directly or
    indirectly from Microsoft, a perpetual, worldwide, non-exclusive, royalty-free, irrevocable license under
    Your patent claims that are necessarily infringed by the Submission or the combination of the
    Submission with the Project to which it was Submitted to make, have made, use, offer to sell, sell and
    import or otherwise dispose of the Submission alone or with the Project.
  • Other Rights Reserved. Each party reserves all rights not expressly granted in this Agreement.
    No additional licenses or rights whatsoever (including, without limitation, any implied licenses) are
    granted by implication, exhaustion, estoppel or otherwise.
  1. Representations and Warranties. You represent that You are legally entitled to grant the above
    licenses. You represent that each of Your Submissions is entirely Your original work (except as You may
    have disclosed under Section 3). You represent that You have secured permission from Your employer to
    make the Submission in cases where Your Submission is made in the course of Your work for Your
    employer or Your employer has intellectual property rights in Your Submission by contract or applicable
    law. If You are signing this Agreement on behalf of Your employer, You represent and warrant that You
    have the necessary authority to bind the listed employer to the obligations contained in this Agreement.
    You are not expected to provide support for Your Submission, unless You choose to do so. UNLESS
    REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, AND EXCEPT FOR THE WARRANTIES
    EXPRESSLY STATED IN SECTIONS 3, 4, AND 6, THE SUBMISSION PROVIDED UNDER THIS AGREEMENT IS
    PROVIDED WITHOUT WARRANTY OF ANY KIND, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTY OF
    NONINFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
  2. Notice to Microsoft. You agree to notify Microsoft in writing of any facts or circumstances of which
    You later become aware that would make Your representations in this Agreement inaccurate in any
    respect.
  3. Information about Submissions. You agree that contributions to Projects and information about
    contributions may be maintained indefinitely and disclosed publicly, including Your name and other
    information that You submit with Your Submission.
  4. Governing Law/Jurisdiction. This Agreement is governed by the laws of the State of Washington, and
    the parties consent to exclusive jurisdiction and venue in the federal courts sitting in King County,
    Washington, unless no federal subject matter jurisdiction exists, in which case the parties consent to
    exclusive jurisdiction and venue in the Superior Court of King County, Washington. The parties waive all
    defenses of lack of personal jurisdiction and forum non-conveniens.
  5. Entire Agreement/Assignment. This Agreement is the entire agreement between the parties, and
    supersedes any and all prior agreements, understandings or communications, written or oral, between
    the parties relating to the subject matter hereof. This Agreement may be assigned by Microsoft.

@microsoft-github-policy-service agree [company="Cohere"]

@Anirudh31415926535
Copy link
Contributor Author

@Anirudh31415926535 please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.

@microsoft-github-policy-service agree [company="{your company}"]

Options:

  • (default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
  • (when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"

Contributor License Agreement

@microsoft-github-policy-service agree company="Cohere"

@thinkall thinkall added this pull request to the merge queue Aug 28, 2024
Merged via the queue into microsoft:main with commit 5861bd9 Aug 28, 2024
142 of 154 checks passed
open-autogen pushed a commit to autogenhub/autogen that referenced this pull request Sep 6, 2024
* Add support for tool calling cohere

* update tool calling code

* make client name configurable with default

* formatting nits

* update docs

---------

Co-authored-by: Mark Sze <[email protected]>
Co-authored-by: Li Jiang <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
models Pertains to using alternate, non-GPT, models (e.g., local models, llama, etc.)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants