0

On the ingestion part to the graph db, I pass a json file, as an episode, custom entities (and edges), using gemini api, but I get some discrepancy on the structured output, like so:

LLM generation failed parsing as JSON, will try to salvage."
Input messages: [
  {
    "parts": [
      {
        "video_metadata": null,
        "thought": null,
        "inline_data": null,
        "file_data": null,
        "thought_signature": null,
        "code_execution_result": null,
        "executable_code": null,
        "function_call": null,
        "function_response": null,
        "text": "\n\n        <MESSAGES>\n        [\n  \"{\\\"entities\\\": [{\\\"id\\\": \\\"invoice_ted-a-29896\\\", \\\"type\\\": \\\"InvoiceEntity\\\", \\\"doc_code\\\": \\\"TED-A-29896\\\", \\\"doc_registration_date\\\": \\\"10/1/2025\\\", \\\"reason\\\": \\\"\\\", \\\"description\\\": \\\"Expense Invoice\\\", \\\"activity_code\\\": \\\"SaaS\\\", \\\"business_unit_code\\\": \\\"MM_SOUTH\\\", \\\"dimension1_code............ d \\", 'entity_types': ['Entity', 'CanonicalItemEntity'], 'attributes': {'labels': ['Entity', 'CanonicalItemEntity']}}\n        </ENTITY>\n        "
      }
    ],
    "role": "user"
  }
]

Has anyone encountered this?

Improve this question
1
Related questions
10
litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call
1
Incremental parsing of LLM output
1
Streaming LLM output in Django

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.