community: set default output_token_limit value for PowerBIToolkit to fix validation error
#26308
Conversation
This file contains 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
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
dosubot
bot
added
size:XS
ccurme
approved these changes
Nov 4, 2024
dosubot
bot
added
the
lgtm
|
Wondering if it is preferable / possible to update |
shjunn
pushed a commit
to shjunn/langchain
that referenced
this pull request
Nov 4, 2024
…` to fix validation error (langchain-ai#26308) ### Description: This PR sets a default value of `output_token_limit = 4000` for the `PowerBIToolkit` to fix the unintentionally validation error. ### Problem: When attempting to run a code snippet from [Langchain's PowerBI toolkit documentation](https://python.langchain.com/v0.1/docs/integrations/toolkits/powerbi/) to interact with a `PowerBIDataset`, the following error occurs: ``` pydantic.v1.error_wrappers.ValidationError: 1 validation error for QueryPowerBITool output_token_limit none is not an allowed value (type=type_error.none.not_allowed) ``` ### Root Cause: The issue arises because when creating a `QueryPowerBITool`, the `output_token_limit` parameter is unintentionally set to `None`, which is the current default for `PowerBIToolkit`. However, `QueryPowerBITool` expects a default value of `4000` for `output_token_limit`. This unintended override causes the error. https://github.com/langchain-ai/langchain/blob/17659ca2cdc418436edf2f8c7f50e800dbbf31ca/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py#L63 https://github.com/langchain-ai/langchain/blob/17659ca2cdc418436edf2f8c7f50e800dbbf31ca/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py#L72-L79 https://github.com/langchain-ai/langchain/blob/17659ca2cdc418436edf2f8c7f50e800dbbf31ca/libs/community/langchain_community/tools/powerbi/tool.py#L39 ### Solution: To resolve this, the default value of `output_token_limit` is now explicitly set to `4000` in `PowerBIToolkit` to prevent the accidental assignment of `None`. Co-authored-by: ccurme <[email protected]>
yanomaly
pushed a commit
to yanomaly/langchain
that referenced
this pull request
Nov 8, 2024
…` to fix validation error (langchain-ai#26308) ### Description: This PR sets a default value of `output_token_limit = 4000` for the `PowerBIToolkit` to fix the unintentionally validation error. ### Problem: When attempting to run a code snippet from [Langchain's PowerBI toolkit documentation](https://python.langchain.com/v0.1/docs/integrations/toolkits/powerbi/) to interact with a `PowerBIDataset`, the following error occurs: ``` pydantic.v1.error_wrappers.ValidationError: 1 validation error for QueryPowerBITool output_token_limit none is not an allowed value (type=type_error.none.not_allowed) ``` ### Root Cause: The issue arises because when creating a `QueryPowerBITool`, the `output_token_limit` parameter is unintentionally set to `None`, which is the current default for `PowerBIToolkit`. However, `QueryPowerBITool` expects a default value of `4000` for `output_token_limit`. This unintended override causes the error. https://github.com/langchain-ai/langchain/blob/17659ca2cdc418436edf2f8c7f50e800dbbf31ca/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py#L63 https://github.com/langchain-ai/langchain/blob/17659ca2cdc418436edf2f8c7f50e800dbbf31ca/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py#L72-L79 https://github.com/langchain-ai/langchain/blob/17659ca2cdc418436edf2f8c7f50e800dbbf31ca/libs/community/langchain_community/tools/powerbi/tool.py#L39 ### Solution: To resolve this, the default value of `output_token_limit` is now explicitly set to `4000` in `PowerBIToolkit` to prevent the accidental assignment of `None`. Co-authored-by: ccurme <[email protected]>
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.
Description:
This PR sets a default value of
output_token_limit = 4000for thePowerBIToolkitto fix the unintentionally validation error.Problem:
When attempting to run a code snippet from Langchain's PowerBI toolkit documentation to interact with a
PowerBIDataset, the following error occurs:Root Cause:
The issue arises because when creating a
QueryPowerBITool, theoutput_token_limitparameter is unintentionally set toNone, which is the current default forPowerBIToolkit. However,QueryPowerBIToolexpects a default value of4000foroutput_token_limit. This unintended override causes the error.langchain/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py
Line 63 in 17659ca
langchain/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py
Lines 72 to 79 in 17659ca
langchain/libs/community/langchain_community/tools/powerbi/tool.py
Line 39 in 17659ca
Solution:
To resolve this, the default value of
output_token_limitis now explicitly set to4000inPowerBIToolkitto prevent the accidental assignment ofNone.