added support for different types in ResponseSchema class #5789
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
…with more structurated json schema
…ore structurated json schema
vowelparrot
approved these changes
Jun 6, 2023
|
Thanks! |
hwchase17
approved these changes
Jun 7, 2023
Undertone0809
pushed a commit
to Undertone0809/langchain
that referenced
this pull request
Jun 19, 2023
…ai#5789) I added support for specifing different types with ResponseSchema objects: ## before ` extracted_info = ResponseSchema(name="extracted_info", description="List of extracted information") ` generate the following doc: ```json\n{\n\t\"extracted_info\": string // List of extracted information}``` This brings GPT to create a JSON with only one string in the specified field even if you requested a List in the description. ## now `extracted_info = ResponseSchema(name="extracted_info", type="List[string]", description="List of extracted information") ` generate the following doc: ```json\n{\n\t\"extracted_info\": List[string] // List of extracted information}``` This way the model responds better to the prompt generating an array of strings. Tag maintainers/contributors who might be interested: Agents / Tools / Toolkits @vowelparrot Don't know who can be interested, I suppose this is a tool, so I tagged you vowelparrot, anyway, it's a minor change, and shouldn't impact any other part of the framework.
kacperlukawski
pushed a commit
to kacperlukawski/langchain
that referenced
this pull request
Jun 29, 2023
…ai#5789) I added support for specifing different types with ResponseSchema objects: ## before ` extracted_info = ResponseSchema(name="extracted_info", description="List of extracted information") ` generate the following doc: ```json\n{\n\t\"extracted_info\": string // List of extracted information}``` This brings GPT to create a JSON with only one string in the specified field even if you requested a List in the description. ## now `extracted_info = ResponseSchema(name="extracted_info", type="List[string]", description="List of extracted information") ` generate the following doc: ```json\n{\n\t\"extracted_info\": List[string] // List of extracted information}``` This way the model responds better to the prompt generating an array of strings. Tag maintainers/contributors who might be interested: Agents / Tools / Toolkits @vowelparrot Don't know who can be interested, I suppose this is a tool, so I tagged you vowelparrot, anyway, it's a minor change, and shouldn't impact any other part of the framework.
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.
I added support for specifing different types with ResponseSchema objects:
before
extracted_info = ResponseSchema(name="extracted_info", description="List of extracted information")generate the following doc:
json\n{\n\t\"extracted_info\": string // List of extracted information}This brings GPT to create a JSON with only one string in the specified field even if you requested a List in the description.
now
extracted_info = ResponseSchema(name="extracted_info", type="List[string]", description="List of extracted information")generate the following doc:
json\n{\n\t\"extracted_info\": List[string] // List of extracted information}This way the model responds better to the prompt generating an array of strings.
Tag maintainers/contributors who might be interested:
Agents / Tools / Toolkits
@vowelparrot
Don't know who can be interested, I suppose this is a tool, so I tagged you vowelparrot,
anyway, it's a minor change, and shouldn't impact any other part of the framework.