Documentation Type
Missing documentation
Documentation Location
I am trying to setup cognee for using the qwen/qwen3-4b-2507 via the Lm Studio. I was able to configure the lm studio to use open ai like endpoint http://localhost:1234/v1. I have configured the ,env in the cognee project directory to the following values
LLM_PROVIDER="custom"
LLM_MODEL="lm_studio/qwen/qwen3-4b-2507"
LLM_ENDPOINT="http://localhost:1234/v1"
LLM_API_KEY="lm-studio"
LITELLM_RESPONSE_FORMAT_TYPE=text
Optional fallback chain
FALLBACK_MODEL=
FALLBACK_ENDPOINT=
FALLBACK_API_KEY=
the code is a simple extract as below
import asyncio
import cognee
custom_prompt = """
Extract only people and cities as entities.
Connect people to cities with the relationship "lives_in".
Ignore all other entities.
"""
async def main():
await cognee.add([
"Alice moved to Paris in 2010, while Bob has always lived in New York.",
"Andreas was born in Venice, but later settled in Lisbon.",
"Diana and Tom were born and raised in Helsingy. Diana currently resides in Berlin, while Tom never moved."
])
if name == "main":
asyncio.run(main())
This always results in the following error
litellm.BadRequestError: Lm_studioException - Error code: 400 - {'error': "'response_format.type' must be 'json_schema' or 'text'"}
Is there any other configuration that I am missing here .Kindly advise.
Regards
Issue Description
There isnt much information about custom localllms.
Suggested Improvement
By including additional instructions if any.
Additional Context
No response
Pre-submission Checklist
Documentation Type
Missing documentation
Documentation Location
I am trying to setup cognee for using the qwen/qwen3-4b-2507 via the Lm Studio. I was able to configure the lm studio to use open ai like endpoint http://localhost:1234/v1. I have configured the ,env in the cognee project directory to the following values
LLM_PROVIDER="custom"
LLM_MODEL="lm_studio/qwen/qwen3-4b-2507"
LLM_ENDPOINT="http://localhost:1234/v1"
LLM_API_KEY="lm-studio"
LITELLM_RESPONSE_FORMAT_TYPE=text
Optional fallback chain
FALLBACK_MODEL=
FALLBACK_ENDPOINT=
FALLBACK_API_KEY=
the code is a simple extract as below
import asyncio
import cognee
custom_prompt = """
Extract only people and cities as entities.
Connect people to cities with the relationship "lives_in".
Ignore all other entities.
"""
async def main():
await cognee.add([
"Alice moved to Paris in 2010, while Bob has always lived in New York.",
"Andreas was born in Venice, but later settled in Lisbon.",
"Diana and Tom were born and raised in Helsingy. Diana currently resides in Berlin, while Tom never moved."
])
if name == "main":
asyncio.run(main())
This always results in the following error
litellm.BadRequestError: Lm_studioException - Error code: 400 - {'error': "'response_format.type' must be 'json_schema' or 'text'"}
Is there any other configuration that I am missing here .Kindly advise.
Regards
Issue Description
There isnt much information about custom localllms.
Suggested Improvement
By including additional instructions if any.
Additional Context
No response
Pre-submission Checklist