Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #2898] [BUG]: Wrong Gemini model names and 500 Internal Server Error #1847

New Issue
Closed
opened 2026-02-22 18:26:49 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:26:49 -05:00
Owner
Copy Link
Copy Source

Originally created by @DangerousBerries on GitHub (Dec 25, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2898

How are you running AnythingLLM?

Docker (local)

What happened?

When selecting the first "Gemini Experimental 1206" from the Chat Model Selection list (there are six overall on the list), It's apparently using gemini-1.5-pro-exp-0801, not 1206, since I'm getting this error:

Could not respond to message.
[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-exp-0801:streamGenerateContent?alt=sse: [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting

When I select the correct "Gemini Experimental 1206" (the forth one top to bottom on the list) and try to send a prompt message, I get the same error just with the correct model.

Could not respond to message.
[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-exp-1206:streamGenerateContent?alt=sse: [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting

Sucks that I've apparently been using 0801all this time before this error started, at least now I know.

Edit: The 500 Internal Server Error is gone now, the model names bug is still there though. I also have a few more comments:

  • The metrics say the LLM's reply takes a few seconds but it actually takes a few minutes to stop loading and show up sometimes, why is that?

  • Gemini 2.0 Flash Thinking Experimental is showing the thinking process in the reply and gets broken easily, using wrong context for its replies.

Originally created by @DangerousBerries on GitHub (Dec 25, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2898 ### How are you running AnythingLLM? Docker (local) ### What happened? When selecting the first "Gemini Experimental 1206" from the Chat Model Selection list (there are six overall on the list), It's apparently using gemini-1.5-pro-exp-0801, not 1206, since I'm getting this error: Could not respond to message. [GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-exp-0801:streamGenerateContent?alt=sse: [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting When I select the correct "Gemini Experimental 1206" (the forth one top to bottom on the list) and try to send a prompt message, I get the same error just with the correct model. Could not respond to message. [GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-exp-1206:streamGenerateContent?alt=sse: [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting Sucks that I've apparently been using 0801all this time before this error started, at least now I know. Edit: The 500 Internal Server Error is gone now, the model names bug is still there though. I also have a few more comments: - The metrics say the LLM's reply takes a few seconds but it actually takes a few minutes to stop loading and show up sometimes, why is that? - Gemini 2.0 Flash Thinking Experimental is showing the thinking process in the reply and gets broken easily, using wrong context for its replies.
yindo added the possible bug label 2026-02-22 18:26:49 -05:00
yindo closed this issue 2026-02-22 18:26:49 -05:00
yindo commented 2026-02-22 18:26:49 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 28, 2024):

The names returned directly from google are wrong for their own ids

{
  name: 'models/gemini-1.5-pro-exp-0801',
  version: 'exp-0801',
  displayName: 'Gemini Experimental 1206',
  description: 'Experimental release (December 6th, 2024) of Gemini.',
  inputTokenLimit: 2097152,
  outputTokenLimit: 8192,
  supportedGenerationMethods: [ 'generateContent', 'countTokens' ],
  temperature: 1,
  topP: 0.95,
  topK: 64,
  maxTemperature: 2
}
{
  name: 'models/gemini-1.5-pro-exp-0827',
  version: 'exp-1206',
  displayName: 'Gemini Experimental 1206',
  description: 'Experimental release (December 6th, 2024) of Gemini.',
  inputTokenLimit: 2097152,
  outputTokenLimit: 8192,
  supportedGenerationMethods: [ 'generateContent', 'countTokens' ],
  temperature: 1,
  topP: 0.95,
  topK: 64,
  maxTemperature: 2
}

We just show the name and as a result, there are 3 "duplicate" entries for the same name - will change this to the ID since this is confusing not knowing exactly which key you chose since we can only fit so much into the input selector.

Also your error

exp-0801:streamGenerateContent?alt=sse: [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting

Is from Google, not us - they must have had downtime on their servers and you hit their API during this time. There is nothing we can do to patch that.

@timothycarambat commented on GitHub (Dec 28, 2024): The names returned directly from google are wrong for their own ids ``` { name: 'models/gemini-1.5-pro-exp-0801', version: 'exp-0801', displayName: 'Gemini Experimental 1206', description: 'Experimental release (December 6th, 2024) of Gemini.', inputTokenLimit: 2097152, outputTokenLimit: 8192, supportedGenerationMethods: [ 'generateContent', 'countTokens' ], temperature: 1, topP: 0.95, topK: 64, maxTemperature: 2 } { name: 'models/gemini-1.5-pro-exp-0827', version: 'exp-1206', displayName: 'Gemini Experimental 1206', description: 'Experimental release (December 6th, 2024) of Gemini.', inputTokenLimit: 2097152, outputTokenLimit: 8192, supportedGenerationMethods: [ 'generateContent', 'countTokens' ], temperature: 1, topP: 0.95, topK: 64, maxTemperature: 2 } ``` We just show the name and as a result, there are 3 "duplicate" entries for the same name - will change this to the ID since this is confusing not knowing exactly which key you chose since we can only fit so much into the input selector. Also your error > [exp-0801:streamGenerateContent?alt=sse](https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-exp-0801:streamGenerateContent?alt=sse): [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting Is from Google, not us - they must have had downtime on their servers and you hit their API during this time. There is nothing we can do to patch that.
yindo commented 2026-02-22 18:26:49 -05:00
Author
Owner
Copy Link
Copy Source

@DangerousBerries commented on GitHub (Dec 30, 2024):

The names returned directly from google are wrong for their own ids

{
  name: 'models/gemini-1.5-pro-exp-0801',
  version: 'exp-0801',
  displayName: 'Gemini Experimental 1206',
  description: 'Experimental release (December 6th, 2024) of Gemini.',
  inputTokenLimit: 2097152,
  outputTokenLimit: 8192,
  supportedGenerationMethods: [ 'generateContent', 'countTokens' ],
  temperature: 1,
  topP: 0.95,
  topK: 64,
  maxTemperature: 2
}
{
  name: 'models/gemini-1.5-pro-exp-0827',
  version: 'exp-1206',
  displayName: 'Gemini Experimental 1206',
  description: 'Experimental release (December 6th, 2024) of Gemini.',
  inputTokenLimit: 2097152,
  outputTokenLimit: 8192,
  supportedGenerationMethods: [ 'generateContent', 'countTokens' ],
  temperature: 1,
  topP: 0.95,
  topK: 64,
  maxTemperature: 2
}

We just show the name and as a result, there are 3 "duplicate" entries for the same name - will change this to the ID since this is confusing not knowing exactly which key you chose since we can only fit so much into the input selector.

Also your error

exp-0801:streamGenerateContent?alt=sse: [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting

Is from Google, not us - they must have had downtime on their servers and you hit their API during this time. There is nothing we can do to patch that.

Thank you. Any idea regarding the sometimes slow loading times of messages? even though the metrics show a few seconds?

@DangerousBerries commented on GitHub (Dec 30, 2024): > The names returned directly from google are wrong for their own ids > > ``` > { > name: 'models/gemini-1.5-pro-exp-0801', > version: 'exp-0801', > displayName: 'Gemini Experimental 1206', > description: 'Experimental release (December 6th, 2024) of Gemini.', > inputTokenLimit: 2097152, > outputTokenLimit: 8192, > supportedGenerationMethods: [ 'generateContent', 'countTokens' ], > temperature: 1, > topP: 0.95, > topK: 64, > maxTemperature: 2 > } > { > name: 'models/gemini-1.5-pro-exp-0827', > version: 'exp-1206', > displayName: 'Gemini Experimental 1206', > description: 'Experimental release (December 6th, 2024) of Gemini.', > inputTokenLimit: 2097152, > outputTokenLimit: 8192, > supportedGenerationMethods: [ 'generateContent', 'countTokens' ], > temperature: 1, > topP: 0.95, > topK: 64, > maxTemperature: 2 > } > ``` > > We just show the name and as a result, there are 3 "duplicate" entries for the same name - will change this to the ID since this is confusing not knowing exactly which key you chose since we can only fit so much into the input selector. > > Also your error > > > [exp-0801:streamGenerateContent?alt=sse](https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-exp-0801:streamGenerateContent?alt=sse): [500 Internal Server Error] An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting > > Is from Google, not us - they must have had downtime on their servers and you hit their API during this time. There is nothing we can do to patch that. Thank you. Any idea regarding the sometimes slow loading times of messages? even though the metrics show a few seconds?
yindo changed title from [BUG]: Wrong Gemini model names and 500 Internal Server Error to [GH-ISSUE #2898] [BUG]: Wrong Gemini model names and 500 Internal Server Error 2026-06-05 14:43:01 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1847
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?