arbs-io/vscode-openai

Error 404, when using the 'query resources' function

Opened this issue · 0 comments

The upload of files and focused querying of those files is a super-feature of vscode-openai !

However - I get this output :
Error: 404 This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?

The chat stands still after that.

However , the log output from the extensions give me this :

2024-11-14 10:26:29.661 [debug]		event - Deleting conversation: c1e339de-59a8-4a29-9e44-b939ef6a10c7
2024-11-14 10:31:08.011 [debug]		event - setting serviceProvider OpenAI
2024-11-14 10:31:08.014 [debug]		event - setting baseUrl https://api.openai.com/v1
2024-11-14 10:31:08.049 [debug]		event - setting defaultModel gpt-4o-realtime-preview-2024-10-01
2024-11-14 10:31:08.056 [debug]		event - setting azureDeployment setup-required
2024-11-14 10:31:08.079 [debug]		event - setting scmModel gpt-4o-realtime-preview-2024-10-01
2024-11-14 10:31:08.084 [debug]		event - setting scmDeployment setup-required
2024-11-14 10:31:08.085 [debug]		event - setting embeddingModel text-embedding-ada-002
2024-11-14 10:31:08.086 [debug]		event - setting embeddingsDeployment setup-required
2024-11-14 10:31:08.086 [debug]		event - setting azureApiVersion 2024-06-01
2024-11-14 10:31:09.154 [info]		event - verifyApiKey success
2024-11-14 10:31:09.156 [info]		setting_configuration - event properties
{
  "vscode_version": "1.95.2",
  "vscode_ui_kind": "desktop",
  "vscode_language": "en",
  "extension_version": "1.6.13",
  "service_provider": "OpenAI",
  "host": "api.openai.com",
  "base_url": "https://api.openai.com/v1",
  "inference_model": "gpt-4o-realtime-preview-2024-10-01",
  "inference_deploy": "setup-required",
  "scm_model": "gpt-4o-realtime-preview-2024-10-01",
  "scm_deploy": "setup-required",
  "embeddings_model": "text-embedding-ada-002",
  "embeddings_deploy": "setup-required",
  "az_api_version": "2024-06-01"
}
2024-11-14 10:32:16.060 [debug]		event - file-index: c:\Users\MDX114\Documents\Pythonworkspace\dbtprojects\ab_analys_dbt\analys-dbt\dbt\models\tableau\tableau__ungadashen_table01_rt.sql
2024-11-14 10:32:16.060 [debug]		event - embedding-controller memory-buffer
2024-11-14 10:32:16.061 [info]		file_information - event properties
{
  "path": "/C:/Users/MDX114/Documents/Pythonworkspace/dbtprojects/ab_analys_dbt/analys-dbt/dbt/models/tableau/tableau__ungadashen_table01_rt.sql",
  "extension": "txt",
  "mimetype": "text/plain",
  "length": "8643"
}
2024-11-14 10:32:17.065 [debug]		event - embedding-controller embedding 8 (chunks)
2024-11-14 10:32:28.890 [debug]		event - file-index: c:\Users\MDX114\Documents\Pythonworkspace\dbtprojects\ab_analys_dbt\analys-dbt\dbt\models\tableau\tableau__ungadashen_table02_rt.sql
2024-11-14 10:32:28.890 [debug]		event - embedding-controller memory-buffer
2024-11-14 10:32:28.890 [info]		file_information - event properties
{
  "path": "/C:/Users/MDX114/Documents/Pythonworkspace/dbtprojects/ab_analys_dbt/analys-dbt/dbt/models/tableau/tableau__ungadashen_table02_rt.sql",
  "extension": "txt",
  "mimetype": "text/plain",
  "length": "8728"
}
2024-11-14 10:32:29.718 [debug]		event - embedding-controller embedding 8 (chunks)
2024-11-14 10:32:32.832 [debug]		event - file-index: c:\Users\MDX114\Documents\Pythonworkspace\dbtprojects\ab_analys_dbt\analys-dbt\dbt\models\tableau\tableau__ungadashen_table03_rt.sql
2024-11-14 10:32:32.832 [debug]		event - embedding-controller memory-buffer
2024-11-14 10:32:32.833 [info]		file_information - event properties
{
  "path": "/C:/Users/MDX114/Documents/Pythonworkspace/dbtprojects/ab_analys_dbt/analys-dbt/dbt/models/tableau/tableau__ungadashen_table03_rt.sql",
  "extension": "txt",
  "mimetype": "text/plain",
  "length": "1471"
}
2024-11-14 10:32:33.545 [debug]		event - embedding-controller embedding 2 (chunks)
2024-11-14 10:32:49.117 [debug]		event - embedding-controller: searchQuery: what are these all about - what are they doing ? 
2024-11-14 10:32:49.989 [error]		Error: 404 This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?