Aristote-code:feat-huggingface-chat-template-values - Branch - langchain-ai/langchain

langchain-ai

langchain

Instrumentation

Wall Time

Blog Docs Changelog

feat: Allow passing tokenizer template values to HuggingFace chat models

#31489

Comparing

Aristote-code:feat-huggingface-chat-template-values

(

eb262b1

) with

master

(

ece9e31

)

Improvements: 0

Regressions: 0

Untouched: 13

New: 0

Dropped: 0

Ignored: 0

Benchmarks

Passed

test_init_time

libs/partners/mistralai/tests/unit_tests/test_standard.py::TestMistralStandard::test_init_time

13 ms

12.9 ms

test_stream_time

libs/partners/anthropic/tests/integration_tests/test_standard.py::TestAnthropicStandard::test_stream_time

15.6 ms

test_stream_time

libs/partners/openai/tests/integration_tests/chat_models/test_base_standard.py::TestOpenAIStandard::test_stream_time

1.1 s

test_init_time

libs/partners/xai/tests/unit_tests/test_chat_models_standard.py::TestXAIStandard::test_init_time

3.3 s

test_stream_time

libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py::TestOpenAIStandard::test_stream_time

1.1 s

test_init_time

libs/partners/groq/tests/unit_tests/test_standard.py::TestGroqStandard::test_init_time

1.6 s

test_init_time

libs/partners/openai/tests/unit_tests/chat_models/test_azure_standard.py::TestOpenAIStandard::test_init_time

1.7 s

test_init_time

libs/partners/fireworks/tests/unit_tests/test_standard.py::TestFireworksStandard::test_init_time

6.6 s

test_init_time

libs/partners/deepseek/tests/unit_tests/test_chat_models.py::TestChatDeepSeekUnit::test_init_time

1.6 s

test_stream_time

libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py::TestOpenAIResponses::test_stream_time

481.3 ms

481.4 ms

test_init_time

libs/partners/anthropic/tests/unit_tests/test_standard.py::TestAnthropicStandard::test_init_time

3.8 ms

test_init_time

libs/partners/openai/tests/unit_tests/chat_models/test_responses_standard.py::TestOpenAIResponses::test_init_time

16.8 ms

16.9 ms

test_init_time

libs/partners/openai/tests/unit_tests/chat_models/test_base_standard.py::TestOpenAIStandard::test_init_time

16.7 ms

16.8 ms

Commits

Click on a commit to change the comparison range

Base

master

ece9e31

feat: Allow passing tokenizer template values to HuggingFace chat models This commit introduces two ways for you to customize chat templating when using `ChatHuggingFace`: 1. **Custom Chat Template String**: A new `chat_template` parameter has been added to the `ChatHuggingFace` constructor. This allows you to provide a custom Jinja template string, which will be assigned to `tokenizer.chat_template` after the tokenizer is loaded. This gives you full control over the chat prompt formatting if the default template associated with a model is not suitable or if you want to experiment with different prompt structures. 2. **Dynamic Template Variables via `**kwargs`**: The `_to_chat_prompt` method in `ChatHuggingFace` (which is responsible for formatting messages using `tokenizer.apply_chat_template`) has been modified to accept arbitrary keyword arguments (`**kwargs`). These `kwargs` are then passed directly to `tokenizer.apply_chat_template`. This allows you to define variables in your Jinja chat templates (either the default one or a custom one) and provide values for these variables dynamically during calls to `invoke`, `stream`, `generate`, etc. Unit tests have been added to verify these new functionalities, including setting custom templates and passing keyword arguments to `apply_chat_template`. Documentation has been updated in the `ChatHuggingFace` class docstring and in the HuggingFace integration notebook (`docs/docs/integrations/chat/huggingface.ipynb`) to explain these new features with examples. This change addresses issue #31470 by providing a flexible way for you to pass tokenizer template values, interpreted as HuggingFace chat template strings and variables for those Jinja templates.

d61626a

20 days ago

by google-labs-jules[bot]

feat: Allow passing tokenizer template values to HuggingFace chat models This commit introduces two ways for you to customize chat templating when using `ChatHuggingFace`: 1. **Custom Chat Template String**: A new `chat_template` parameter has been added to the `ChatHuggingFace` constructor. This allows you to provide a custom Jinja template string, which will be assigned to `tokenizer.chat_template` after the tokenizer is loaded. This gives you full control over the chat prompt formatting if the default template associated with a model is not suitable or if you want to experiment with different prompt structures. 2. **Dynamic Template Variables via `**kwargs`**: The `_to_chat_prompt` method in `ChatHuggingFace` (which is responsible for formatting messages using `tokenizer.apply_chat_template`) has been modified to accept arbitrary keyword arguments (`**kwargs`). These `kwargs` are then passed directly to `tokenizer.apply_chat_template`. This allows you to define variables in your Jinja chat templates (either the default one or a custom one) and provide values for these variables dynamically during calls to `invoke`, `stream`, `generate`, etc. Unit tests have been added to verify these new functionalities, including setting custom templates and passing keyword arguments to `apply_chat_template`. Documentation has been updated in the `ChatHuggingFace` class docstring and in the HuggingFace integration notebook (`docs/docs/integrations/chat/huggingface.ipynb`) to explain these new features with examples. Linting errors (E501 Line too long) found in a previous CI run have been fixed. This change addresses issue #31470 by providing a flexible way for you to pass tokenizer template values, interpreted as HuggingFace chat template strings and variables for those Jinja templates.

a822322

20 days ago

by google-labs-jules[bot]

feat: Allow passing tokenizer template values to HuggingFace chat models This commit introduces two ways for you to customize chat templating when using `ChatHuggingFace`: 1. **Custom Chat Template String**: A new `chat_template` parameter has been added to the `ChatHuggingFace` constructor. This allows you to provide a custom Jinja template string, which will be assigned to `tokenizer.chat_template` after the tokenizer is loaded. This gives you full control over the chat prompt formatting if the default template associated with a model is not suitable or if you want to experiment with different prompt structures. 2. **Dynamic Template Variables via `**kwargs`**: The `_to_chat_prompt` method in `ChatHuggingFace` (which is responsible for formatting messages using `tokenizer.apply_chat_template`) has been modified to accept arbitrary keyword arguments (`**kwargs`). These `kwargs` are then passed directly to `tokenizer.apply_chat_template`. This allows you to define variables in your Jinja chat templates (either the default one or a custom one) and provide values for these variables dynamically during calls to `invoke`, `stream`, `generate`, etc. Unit tests have been added to verify these new functionalities, including setting custom templates and passing keyword arguments to `apply_chat_template`. Documentation has been updated in the `ChatHuggingFace` class docstring and in the HuggingFace integration notebook (`docs/docs/integrations/chat/huggingface.ipynb`) to explain these new features with examples. Linting errors (E501 Line too long) found in a previous CI run have been fixed by reformatting dictionary comprehensions and other long lines. This change addresses issue #31470 by providing a flexible way for you to pass tokenizer template values, interpreted as HuggingFace chat template strings and variables for those Jinja templates.

b64ef6f

20 days ago

by google-labs-jules[bot]

feat: Allow passing tokenizer template values to HuggingFace chat models This commit introduces two ways for you to customize chat templating when using `ChatHuggingFace`: 1. **Custom Chat Template String**: A new `chat_template` parameter has been added to the `ChatHuggingFace` constructor. This allows you to provide a custom Jinja template string, which will be assigned to `tokenizer.chat_template` after the tokenizer is loaded. This gives you full control over the chat prompt formatting if the default template associated with a model is not suitable or if you want to experiment with different prompt structures. 2. **Dynamic Template Variables via `**kwargs`**: The `_to_chat_prompt` method in `ChatHuggingFace` (which is responsible for formatting messages using `tokenizer.apply_chat_template`) has been modified to accept arbitrary keyword arguments (`**kwargs`). These `kwargs` are then passed directly to `tokenizer.apply_chat_template`. This allows you to define variables in your Jinja chat templates (either the default one or a custom one) and provide values for these variables dynamically during calls to `invoke`, `stream`, `generate`, etc. Unit tests have been added to verify these new functionalities, including setting custom templates and passing keyword arguments to `apply_chat_template`. Documentation has been updated in the `ChatHuggingFace` class docstring and in the HuggingFace integration notebook (`docs/docs/integrations/chat/huggingface.ipynb`) to explain these new features with examples. Further fixes for E501 (Line too long) linting errors based on CI feedback. This change addresses issue #31470 by providing a flexible way to pass tokenizer template values, interpreted as HuggingFace chat template strings and variables for those Jinja templates.

fddbb29

20 days ago

by google-labs-jules[bot]

feat: Allow passing tokenizer template values to HuggingFace chat models This commit introduces two ways you can customize chat templating when using `ChatHuggingFace`: 1. **Custom Chat Template String**: A new `chat_template` parameter has been added to the `ChatHuggingFace` constructor. This allows you to provide a custom Jinja template string, which will be assigned to `tokenizer.chat_template` after the tokenizer is loaded. This gives you full control over the chat prompt formatting if the default template associated with a model is not suitable or if you want to experiment with different prompt structures. 2. **Dynamic Template Variables via `**kwargs`**: The `_to_chat_prompt` method in `ChatHuggingFace` (which is responsible for formatting messages using `tokenizer.apply_chat_template`) has been modified to accept arbitrary keyword arguments (`**kwargs`). These `kwargs` are then passed directly to `tokenizer.apply_chat_template`. This allows you to define variables in your Jinja chat templates (either the default one or a custom one) and provide values for these variables dynamically during calls to `invoke`, `stream`, `generate`, etc. Unit tests have been added to verify these new functionalities, including setting custom templates and passing keyword arguments to `apply_chat_template`. Documentation has been updated in the `ChatHuggingFace` class docstring and in the HuggingFace integration notebook (`docs/docs/integrations/chat/huggingface.ipynb`) to explain these new features with examples. This commit also includes comprehensive linting and formatting fixes for the `libs/partners/huggingface` directory to align with project standards, including `pyupgrade`, `ruff`, `black`, and `isort` changes. This change addresses issue #31470 by providing a flexible way to pass tokenizer template values, interpreted as HuggingFace chat template strings and variables for those Jinja templates.

02a1bdb

20 days ago

by google-labs-jules[bot]

feat: Allow passing tokenizer template values to HuggingFace chat models This commit introduces two ways to customize chat templating when using `ChatHuggingFace`: 1. **Custom Chat Template String**: A new `chat_template` parameter has been added to the `ChatHuggingFace` constructor. This allows you to provide a custom Jinja template string, which will be assigned to `tokenizer.chat_template` after the tokenizer is loaded. This gives you full control over the chat prompt formatting if the default template associated with a model is not suitable or if you want to experiment with different prompt structures. 2. **Dynamic Template Variables via `**kwargs`**: The `_to_chat_prompt` method in `ChatHuggingFace` (which is responsible for formatting messages using `tokenizer.apply_chat_template`) has been modified to accept arbitrary keyword arguments (`**kwargs`). These `kwargs` are then passed directly to `tokenizer.apply_chat_template`. This allows you to define variables in your Jinja chat templates (either the default one or a custom one) and provide values for these variables dynamically during calls to `invoke`, `stream`, `generate`, etc. Unit tests have been added to verify these new functionalities, including setting custom templates and passing keyword arguments to `apply_chat_template`. Documentation has been updated in the `ChatHuggingFace` class docstring and in the HuggingFace integration notebook (`docs/docs/integrations/chat/huggingface.ipynb`) to explain these new features with examples. This commit also includes comprehensive linting and formatting fixes for the `libs/partners/huggingface` directory to align with project standards, including `pyupgrade`, `ruff --fix`, `black`, `isort`, and `ruff format` changes. This change addresses issue #31470 by providing a flexible way to pass tokenizer template values, interpreted as HuggingFace chat template strings and variables for those Jinja templates.

5aba416

20 days ago

by google-labs-jules[bot]

feat: Allow passing tokenizer template values to HuggingFace chat models This commit introduces two ways you can customize chat templating when using `ChatHuggingFace`: 1. **Custom Chat Template String**: A new `chat_template` parameter has been added to the `ChatHuggingFace` constructor. This allows you to provide a custom Jinja template string, which will be assigned to `tokenizer.chat_template` after the tokenizer is loaded. This gives you full control over the chat prompt formatting if the default template associated with a model is not suitable or if you want to experiment with different prompt structures. 2. **Dynamic Template Variables via `**kwargs`**: The `_to_chat_prompt` method in `ChatHuggingFace` (which is responsible for formatting messages using `tokenizer.apply_chat_template`) has been modified to accept arbitrary keyword arguments (`**kwargs`). These `kwargs` are then passed directly to `tokenizer.apply_chat_template`. This allows you to define variables in your Jinja chat templates (either the default one or a custom one) and provide values for these variables dynamically during calls to `invoke`, `stream`, `generate`, etc. Unit tests have been added to verify these new functionalities, including setting custom templates and passing keyword arguments to `apply_chat_template`. Documentation has been updated in the `ChatHuggingFace` class docstring and in the HuggingFace integration notebook (`docs/docs/integrations/chat/huggingface.ipynb`) to explain these new features with examples. This commit also includes comprehensive linting and formatting fixes for the `libs/partners/huggingface` directory to align with project standards. This includes: - Fixing E501 (line too long) errors. - Correcting an invalid `type: ignore[import]` comment in `llms/huggingface_endpoint.py`. - Resolving an `AttributeError` in mypy for `tests/unit_tests/test_chat_models.py`. - Ensuring `pyupgrade`, `ruff`, `black`, and `isort` checks pass. This change addresses issue #31470 by providing a flexible way to pass tokenizer template values, interpreted as HuggingFace chat template strings and variables for those Jinja templates.

eb262b1

17 days ago

by google-labs-jules[bot]

Home Terms Privacy Docs