Title convo broken on main #8338
Replies: 14 comments 9 replies
-
|
Here's my config and it works well, try removing endpoints:
azureOpenAI:
streamRate: 35
titleModel: "grok-3"
titleConvo: true
groups:
- group: "eastus"
apiKey: "${REGION_API_KEY}"
assistants: true
instanceName: "instance-eastus"
version: "2024-02-15-preview"
models:
gpt-4o:
deploymentName: gpt-4o
- group: "region-eastus"
apiKey: "${REGION2_API_KEY}"
instanceName: "instance-eastus2"
version: "2024-12-01-preview"
models:
gpt-4o-latest:
deploymentName: "gpt-4o-mini"
version: "2024-02-15-preview"
o1-mini:
deploymentName: "o1-mini"
o1-preview:
deploymentName: "o1-preview"
o3-mini:
deploymentName: "o3-mini"
o4-mini-region2:
deploymentName: "o4-mini-region2"
gpt-4.1:
deploymentName: "gpt-4.1"
gpt-4.1-mini:
deploymentName: "gpt-4.1-mini-region2"
gpt-4.1-nano:
deploymentName: "gpt-4.1-nano"
o3-pro:
deploymentName: "o3-pro"
version: "2025-04-01-preview"
- group: "codex-mini"
apiKey: "${GENERIC_API_KEY}"
baseURL: "https://generic-instance-region2.cognitiveservices.azure.com/openai/"
version: "2025-04-01-preview"
serverless: true
models:
codex-mini:
deploymentName: "codex-mini"
- group: "model-group"
apiKey: "${GENERIC_API_KEY}"
instanceName: "generic-instance-region2"
version: "2025-03-01-preview"
deploymentName: "model-mini"
models:
model-mini: true
- group: "region-placeholder" # arbitrary name
apiKey: "${REGION_API_KEY}" # arbitrary env. var, must be defined in .env file
instanceName: "generic-instance-name" # the instance
version: "2024-12-01-preview"
models:
o1-2024-12-17:
deploymentName: "o1"
- group: "Azure AI Deepseek"
assistants: false
apiKey: "${DEEPSEEK_API_KEY}"
baseURL: "https://DeepSeek-R1-LC.region2.models.ai.azure.com/v1/"
version: "2024-08-01-preview"
serverless: true
models:
DeepSeek-R1:
deploymentName: "DeepSeek-R1"
- group: "Azure AI Foundry"
apiKey: "${GENERIC_API_KEY}"
baseURL: "https://generic-instance-region2.services.ai.azure.com/models"
version: "2024-05-01-preview"
serverless: true
dropParams: ["stream_options", "user"]
models:
Mistral-Large-2411:
deploymentName: "Mistral-Large-2411"
grok-3:
deploymentName: "grok-3"
|
Beta Was this translation helpful? Give feedback.
-
|
Removed titleMethod, still not working..
Isn’t this a bug rather than a discussion?
Thanks for your help.
…On Wed, 9 Jul 2025 at 18:14, Danny Avila ***@***.***> wrote:
Here's my config and it works well, try removing titleMethod:
endpoints:
azureOpenAI:
streamRate: 35
titleModel: "grok-3"
titleConvo: true
groups:
- group: "eastus"
apiKey: "${REGION_API_KEY}"
assistants: true
instanceName: "instance-eastus"
version: "2024-02-15-preview"
models:
gpt-4o:
deploymentName: gpt-4o
- group: "region-eastus"
apiKey: "${REGION2_API_KEY}"
instanceName: "instance-eastus2"
version: "2024-12-01-preview"
models:
gpt-4o-latest:
deploymentName: "gpt-4o-mini"
version: "2024-02-15-preview"
o1-mini:
deploymentName: "o1-mini"
o1-preview:
deploymentName: "o1-preview"
o3-mini:
deploymentName: "o3-mini"
o4-mini-region2:
deploymentName: "o4-mini-region2"
gpt-4.1:
deploymentName: "gpt-4.1"
gpt-4.1-mini:
deploymentName: "gpt-4.1-mini-region2"
gpt-4.1-nano:
deploymentName: "gpt-4.1-nano"
o3-pro:
deploymentName: "o3-pro"
version: "2025-04-01-preview"
- group: "codex-mini"
apiKey: "${GENERIC_API_KEY}"
baseURL: "https://generic-instance-region2.cognitiveservices.azure.com/openai/"
version: "2025-04-01-preview"
serverless: true
models:
codex-mini:
deploymentName: "codex-mini"
- group: "model-group"
apiKey: "${GENERIC_API_KEY}"
instanceName: "generic-instance-region2"
version: "2025-03-01-preview"
deploymentName: "model-mini"
models:
model-mini: true
- group: "region-placeholder" # arbitrary name
apiKey: "${REGION_API_KEY}" # arbitrary env. var, must be defined in .env file
instanceName: "generic-instance-name" # the instance
version: "2024-12-01-preview"
models:
o1-2024-12-17:
deploymentName: "o1"
- group: "Azure AI Deepseek"
assistants: false
apiKey: "${DEEPSEEK_API_KEY}"
baseURL: "https://DeepSeek-R1-LC.region2.models.ai.azure.com/v1/"
version: "2024-08-01-preview"
serverless: true
models:
DeepSeek-R1:
deploymentName: "DeepSeek-R1"
- group: "Azure AI Foundry"
apiKey: "${GENERIC_API_KEY}"
baseURL: "https://generic-instance-region2.services.ai.azure.com/models"
version: "2024-05-01-preview"
serverless: true
dropParams: ["stream_options", "user"]
models:
Mistral-Large-2411:
deploymentName: "Mistral-Large-2411"
grok-3:
deploymentName: "grok-3"
chrome_jhRsaX9aVh.png (view on web)
<https://github.com/user-attachments/assets/6921fc76-a3b4-40ba-b0a9-3a53c5524684>
—
Reply to this email directly, view it on GitHub
<#8338 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AAFBEXSXGVHMOWGYD46UCWD3HU5VTAVCNFSM6AAAAACBESX3FGVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNZRGEYDEMA>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
I got the same error after using latest main branch. |
Beta Was this translation helpful? Give feedback.
-
|
Tried a few things but still no go, latest changes seem to have broken title gen. |
Beta Was this translation helpful? Give feedback.
-
|
It's not a bug as I'm not having any issues with titling or reproducing it using Azure or other providers. This specific error happens when the title fails to generate in time. There's not enough logs here from debug logs to help you determine the issue. Log locations:
There are two types of logs that can help diagnose the issue:
Error logs contain exact stack traces and are especially helpful, but both can provide valuable information. Please only include the relevant portions of logs that correspond to when you reproduced the error. |
Beta Was this translation helpful? Give feedback.
-
|
Hi @danny-avila 2025-07-10T22:20:36.653Z debug: [saveConvo] api/app/clients/BaseClient.js - saveMessageToDatabase #saveConvo |
Beta Was this translation helpful? Give feedback.
-
|
Check the error logs (location above in earlier comment), and provide the full info for this particular error:
I'm not able to reproduce, but this will give me more information on what's causing the error on your end. |
Beta Was this translation helpful? Give feedback.
-
|
These I my logs. |
Beta Was this translation helpful? Give feedback.
-
|
I encountered the same issue; the container I launched using the example .env and librechat.yaml. openai: Anthropic: |
Beta Was this translation helpful? Give feedback.
-
|
I'm deploying Librechat on Railway, and while conversations from a few days ago have nice titles, since the latest pull, it's just "New Chat" for everything. Not sure why, but this is looking more like a bug, especially since my yaml config has remained unchanged. |
Beta Was this translation helpful? Give feedback.
-
|
Same, no config change, just pulling.
…On Sun, 13 Jul 2025 at 22:42, Akshay Iyengar ***@***.***> wrote:
I'm deploying Librechat on Railway, and while conversations from a few
days ago have nice titles, since the latest pull, it's just "New Chat" for
everything. Not sure why, but this is looking more like a bug, especially
since my yaml config has remained unchanged.
—
Reply to this email directly, view it on GitHub
<#8338 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AAFBEXRUXJR5RUVPVYXNAVT3ILAETAVCNFSM6AAAAACBESX3FGVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNZUGU3TONY>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
What @danny-avila said seems to be correct. I tried a bunch of different options for titleModel, and only a few actually work. The key seems to be in using a model that actually is able to generate a conversation title. Even sonnet-4 was not great. I asked ChatGPT itself about the issue and was given the following to try:
I switched to gpt-4o and it works just fine. |
Beta Was this translation helpful? Give feedback.
-
|
I have been using gpt-4.1 since the start, have not changed my config, have
recently pulled main, and it has stopped working.
Not sure your suggestion solves the problem for me.
…On Mon, 14 Jul 2025 at 00:10, Akshay Iyengar ***@***.***> wrote:
This specific error happens when the title fails to generate in time.
What @danny-avila <https://github.com/danny-avila> said seems to be
correct. I tried a bunch of different options for titleModel, and only a
few actually work. The key seems to be in using a model that actually is
able to generate a conversation title. Even sonnet-4 was not great. I asked
ChatGPT itself about the issue and was given the following to try:
Model Speed Accuracy
openai/gpt-4o ⚡ Fastest 🧠 Excellent
mistralai/mistral-small-3.2-24b-instruct ⚡⚡ Very Fast 👍 Good
perplexity/sonar-reasoning ⚡ Fast ✅ Very Good
anthropic/claude-sonnet-4 🐢 Slower 🧠 Excellent
mistralai/devstral-small-2505 ⚡⚡ Fastest 🤏 Fair
I switched to gpt-4o and it works just fine.
—
Reply to this email directly, view it on GitHub
<#8338 (reply in thread)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AAFBEXW5GEHUP5AF3W6RFID3ILKMLAVCNFSM6AAAAACBESX3FGVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNZUGYYDCNQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
I was trying to collect the logs, but before I could reproduce the issue, it started working 😅 For what it's worth, here are the steps that fixed the issue for me (I don't know the root cause though):
endpoints:
azureOpenAI:
- titleModel: "gpt-4.1-nano"
+ titleModel: "gpt-4.1"and to try to capture the exception, I set the env values: CONSOLE_JSON=true
CONSOLE_JSON_STRING_LENGTH=2000
The version didn't change, I observed both buggy and working behavior on:
|
Beta Was this translation helpful? Give feedback.
-
|
Same for me. After pulling the latest changes, the title starts working again. I didn't change any of the configuration. Thanks for help |
Beta Was this translation helpful? Give feedback.
-
|
Hi @danny-avila After pulling the latest changes, the title generation is broken again for me (In both Azure OpenAI and Agent endpoint) but the AWS Bedrock endpoint is working for me. The following is the error message from the log file, I did not change any configuration in the LibreChat.yaml file.
Could you please help me about that? |
Beta Was this translation helpful? Give feedback.
-
|
Are you building your own docker image or using NPM directly? I think it’s a module resolution error on your end. More info on how you’re running/installing LC will provide insight. This is not reproducible on official docker images or doing a clean reinstall with node ^20.19.0 |
Beta Was this translation helpful? Give feedback.
-
|
On latest build, using Azure + agent via azure: |
Beta Was this translation helpful? Give feedback.
-
|
Hi @danny-avila |
Beta Was this translation helpful? Give feedback.
-
|
@datacom-jing if building your own image, try to align the installation/build strategy to the official dockerfiles, including node version. otherwise you may have dependency issues like this one.
~/LibreChat$ npm ls @langchain/openai
[email protected] /home/danny/LibreChat
├─┬ @librechat/[email protected] -> ./packages/api
│ └─┬ @librechat/[email protected]
│ ├─┬ @langchain/[email protected]
│ │ └── @langchain/[email protected] deduped
│ ├─┬ @langchain/[email protected]
│ │ └── @langchain/[email protected] deduped
│ ├── @langchain/[email protected] deduped
│ └─┬ @langchain/[email protected]
│ └── @langchain/[email protected] deduped
└─┬ @librechat/[email protected] -> ./api
├─┬ @langchain/[email protected]
│ ├── @langchain/[email protected] deduped
│ └─┬ [email protected]
│ └── @langchain/[email protected] deduped
└── @langchain/[email protected] overridden |
Beta Was this translation helpful? Give feedback.
-
|
I'm still digging into this and I'm certain it's a dependency issue, and looking into how I can make this easier to resolve on different builds. |
Beta Was this translation helpful? Give feedback.
-
|
Closed by #8580 |
Beta Was this translation helpful? Give feedback.
-
|
Thanks for taking the time.
…On Tue, 22 Jul 2025 at 18:09, Danny Avila ***@***.***> wrote:
Closed #8338 <#8338>
as resolved.
—
Reply to this email directly, view it on GitHub
<#8338>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AAFBEXRTLJL22Y7GCUHNJID3JZO47AVCNFSM6AAAAACBESX3FGVHI2DSMVQWIX3LMV45UABFIRUXGY3VONZWS33OIV3GK3TUHI5E433UNFTGSY3BORUW63R3GIYDKOJUGQ2A>
.
You are receiving this because you authored the thread.Message ID:
<danny-avila/LibreChat/repo-discussions/8338/discussion_event/2059444@
github.com>
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
What happened?
Updated to latest main, and title convo stopped working. Was working fine until latest pull.
Got error 404: "Title not found or method not implemented for the conversation's endpoint"
Did these new lines in hooks break it ? :
Version Information
ghcr.io/danny-avila/librechat-dev latest 34280f5146b2 2 days ago 1.1GB
ghcr.io/danny-avila/librechat-rag-api-dev-lite latest 2991e83a1e7b 4 days ago 1.48GB
Steps to Reproduce
Use latest main, new chat with title.
Config:
What browsers are you seeing the problem on?
No response
Relevant log output
{message: "Title not found or method not implemented for the conversation's endpoint"} message : "Title not found or method not implemented for the conversation's endpoint"Screenshots
Code of Conduct
Beta Was this translation helpful? Give feedback.
All reactions