[Feature] Function Calling #2544
Merged
Conversation
This file contains hidden or 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
|
Based on the communication in Slack, I have left some of my review comments. 😄 |
Co-authored-by: Haoyu Wang <120358163+HaoyuWang4188@users.noreply.github.com>
Co-authored-by: Haoyu Wang <120358163+HaoyuWang4188@users.noreply.github.com>
3 tasks
merrymercy
reviewed
Dec 26, 2024
2 tasks
|
@merrymercy @Ying1123 The above comments have been resolved |
merrymercy
requested changes
Dec 28, 2024
|
Done @merrymercy |
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 15, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 15, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 15, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 15, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 15, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
Aaron1011
added a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented.
github-merge-queue bot
pushed a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented. Co-authored-by: Aaron Hill <aaron@tensorzero.com> Co-authored-by: Viraj Mehta <virajmehta@users.noreply.github.com>
github-merge-queue bot
pushed a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
* Add SGLang provider This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented. * Use SGLANG_API_KEY in merge-queue.yml --------- Co-authored-by: Aaron Hill <aaron@tensorzero.com> Co-authored-by: Viraj Mehta <virajmehta@users.noreply.github.com>
github-merge-queue bot
pushed a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
* Add SGLang provider This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented. * Use SGLANG_API_KEY in merge-queue.yml --------- Co-authored-by: Aaron Hill <aaron@tensorzero.com> Co-authored-by: Viraj Mehta <virajmehta@users.noreply.github.com>
github-merge-queue bot
pushed a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
* Add SGLang provider This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented. * Use SGLANG_API_KEY in merge-queue.yml --------- Co-authored-by: Aaron Hill <aaron@tensorzero.com> Co-authored-by: Viraj Mehta <virajmehta@users.noreply.github.com>
github-merge-queue bot
pushed a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
* Add SGLang provider This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented. * Use SGLANG_API_KEY in merge-queue.yml --------- Co-authored-by: Aaron Hill <aaron@tensorzero.com> Co-authored-by: Viraj Mehta <virajmehta@users.noreply.github.com>
github-merge-queue bot
pushed a commit
to tensorzero/tensorzero
that referenced
this pull request
Jan 16, 2025
* Add SGLang provider This is heavily based on the existing OpenAI provider. Current limitations: * SGLang only support JSON output when a json schema is provided, so both 'json_mode = on' and 'json_mode = strict' require a schema to be provided * Tool use was just implemneted in sgl-project/sglang#2544, which is not yet released. For now, we pass through tool parameters using the standard OpenAI API, but log a warning. * Only chat completions (with/without streaming) are currently implemented. * Use SGLANG_API_KEY in merge-queue.yml --------- Co-authored-by: Aaron Hill <aaron@tensorzero.com> Co-authored-by: Viraj Mehta <virajmehta@users.noreply.github.com>
timethink
pushed a commit
to timethink/sglang
that referenced
this pull request
Mar 9, 2025
Co-authored-by: Haoyu Wang <120358163+HaoyuWang4188@users.noreply.github.com>
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.
Motivation
This PR provides support for function calling #2429 . Currently function tooling implemented for tokenizer apply_chat_template. Streaming not support as well for function tooling.
Modifications
Checklist