ValueError Traceback (most recent call last) ----> 1 OpenAI.modelname_to_contextsize('gpt-5')

File /.venv/lib/python3.12/site-packages/langchain_openai/llms/base.py:710, in BaseOpenAI.modelname_to_contextsize(modelname) 707 context_size = model_token_mapping.get(modelname) 709 if context_size is None: --> 710 raise ValueError( 711 f"Unknown model: {modelname}. Please provide a valid OpenAI model name." 712 "Known models are: " + ", ".join(model_token_mapping.keys()) 713 ) 715 return context_size

ValueError: Unknown model: gpt-5. Please provide a valid OpenAI model name.Known models are: gpt-4o-mini, gpt-4o, gpt-4o-2024-05-13, gpt-4, gpt-4-0314, gpt-4-0613, gpt-4-32k, gpt-4-32k-0314, gpt-4-32k-0613, gpt-3.5-turbo, gpt-3.5-turbo-0301, gpt-3.5-turbo-0613, gpt-3.5-turbo-16k, gpt-3.5-turbo-16k-0613, gpt-3.5-turbo-instruct, text-ada-001, ada, text-babbage-001, babbage, text-curie-001, curie, davinci, text-davinci-003, text-davinci-002, code-davinci-002, code-davinci-001, code-cushman-002, code-cushman-001

Problem Summary

The langchain_openai package has a static model name to context size mapping that is incomplete, leading to a ValueError when trying to get the context size for models not present in the mapping.

Root Cause Analysis

The root cause is the incomplete model name to context size mapping in the langchain_openai package.

Fix Plan

Update the model name to context size mapping

1. Clone the langchain repository from GitHub.
2. Update the model_token_mapping dictionary in langchain_openai/llms/base.py to include the missing models.
3. Run pip install -e . to install the updated package.
4. Update the langchain_openai package in your project to the latest version.

Example Code

# langchain_openai/llms/base.py
model_token_mapping = {
    # ... existing mappings ...
    'gpt-4.1': 2048,
    'gpt-4.2': 2048,
    'gpt-5': 4096,
    'gpt-5.1': 4096,
    # ... add more missing models ...
}

Verification

1. Run the reproduction code again to verify that the ValueError is resolved.
2. Check the context size returned for the updated models.

Extra Tips

• Make sure to update the langchain_openai package in your project to the latest version.
• Consider using a dynamic model name to context size mapping instead of a static one.
• If you're using a CI/CD pipeline, update the pipeline to use the updated package.