Unverified50% confidenceSolutionExact time
After setting use_schema_constraints=False, LangExtract requests switch to response_format: {"type": "json_object"}, which works around servers that do not support json_schema.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedIn json_object mode, LangExtract expects bare JSON; if the model returns a JSON block with explanatory text and fences, it is discarded, with the log reading Chunk omitted from results (parse error): Failed to parse JSON content.69% similarUnverifiedWhen the server reports a 422 parameter format error, in addition to checking the JSON syntax, you should also confirm whether the Content-Type matches the request body format—if the request body is JSON but the Content-Type is still the default form format, the server may fail to parse it.69% similarUnverifiedStructured output (JSON schema constraints) can only eliminate the single error of malformed output; other types of errors (such as semantic classification errors) are unaffected.69% similarUnverifiedWhen the server returns 400 for json_schema, LangExtract's extract() throws InferenceRuntimeError: OpenAI API error: Error code: 400.69% similarUnverifiedEventSource only supports GET requests and cannot carry a JSON request body; therefore chat-type endpoints that require POST should switch to using fetch to read the stream.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1066763API
curl https://kongchang.com/api/v1/knowledge/claims/1066763MCP
get_claim(id=1066763)