Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4574] [BUG]: I don't know why I would use an non-existent model #2907

New Issue
Closed
opened 2026-02-22 18:31:46 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:31:46 -05:00
Owner
Copy Link
Copy Source

Originally created by @SKYC829 on GitHub (Oct 23, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4574

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I deployed the local ollama and pulled two small models. I don't know why, but AnythingLLM always uses the previously tested and deleted large model.

Image Image Image Image Image Image Image

Image

Are there known steps to reproduce?

I'm not sure if this step is useful.

  1. Newly installed Ubuntu Server 22.04
  2. Newly installed ollama
  3. Download a large model and set it as both LLM and Embedder in AnythingLLM
  4. Delete this large model, download another large model, and continue to set it as LLM and Embedder in AnythingLLM
  5. Repeat steps 3 and 4 until I find the LLM and Embedder that my server can handle
  6. Upload and embed the file, and try to retrieve file information through the conversation
    Note: Since this is my first attempt at deploying a self-hosted knowledge base with AI, I am not familiar with what LLM and Embedder are. Therefore, when retrying steps 3 and 4, I often confused LLM with Embedder and attempted to upload and embed files.
Originally created by @SKYC829 on GitHub (Oct 23, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4574 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I deployed the local ollama and pulled two small models. I don't know why, but AnythingLLM always uses the previously tested and deleted large model. <img width="1920" height="1017" alt="Image" src="https://github.com/user-attachments/assets/1ffad57a-e5ba-4e6c-9692-1491ddf1d92d" /> <img width="1920" height="1017" alt="Image" src="https://github.com/user-attachments/assets/3f5b89c6-06e8-4c2e-ba9f-ebc789d09243" /> <img width="1920" height="1017" alt="Image" src="https://github.com/user-attachments/assets/3a3555e3-ca37-4346-887e-4afed286a85b" /> <img width="1920" height="1017" alt="Image" src="https://github.com/user-attachments/assets/9c095021-31a5-4c2f-b384-78c2cdd99702" /> <img width="1920" height="1017" alt="Image" src="https://github.com/user-attachments/assets/2480884d-4d6d-4e92-84ae-7e7a2933e6a8" /> <img width="1920" height="1017" alt="Image" src="https://github.com/user-attachments/assets/fc2d3a7e-a67a-4560-921a-3e72122513fe" /> <img width="840" height="700" alt="Image" src="https://github.com/user-attachments/assets/877dcdca-78bd-4927-8ab0-482144e1f454" /> ![Image](https://github.com/user-attachments/assets/cdd24fc6-35ac-499a-948c-721859ac309c) ### Are there known steps to reproduce? I'm not sure if this step is useful. 1. Newly installed Ubuntu Server 22.04 2. Newly installed ollama 3. Download a large model and set it as both LLM and Embedder in AnythingLLM 4. Delete this large model, download another large model, and continue to set it as LLM and Embedder in AnythingLLM 5. Repeat steps 3 and 4 until I find the LLM and Embedder that my server can handle 6. Upload and embed the file, and try to retrieve file information through the conversation Note: Since this is my first attempt at deploying a self-hosted knowledge base with AI, I am not familiar with what LLM and Embedder are. Therefore, when retrying steps 3 and 4, I often confused LLM with Embedder and attempted to upload and embed files.
yindo added the possible bug label 2026-02-22 18:31:46 -05:00
yindo closed this issue 2026-02-22 18:31:46 -05:00
yindo commented 2026-02-22 18:31:46 -05:00
Author
Owner
Copy Link
Copy Source

@SKYC829 commented on GitHub (Oct 23, 2025):

backend log

{"level":"info","message":"\u001b[35m[TokenManager]\u001b[0m Initialized new TokenManager instance for model: gpt-3.5-turbo","service":"backend"}
{"level":"info","message":"\u001b[36m[EncryptionManager]\u001b[0m Loaded existing key & salt for encrypting arbitrary data.","service":"backend"}
{"level":"info","message":"\u001b[33m[ContextWindowFinder]\u001b[0m Pulling remote model map...","service":"backend"}
{"level":"info","message":"\u001b[35m[TokenManager]\u001b[0m Returning existing instance for model: gpt-3.5-turbo","service":"backend"}
{"level":"info","message":"\u001b[32m[TELEMETRY ENABLED]\u001b[0m Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM.","service":"backend"}
{"level":"info","message":"\u001b[33m[ContextWindowFinder]\u001b[0m Error syncing remote model map TypeError: fetch failed\n    at node:internal/deps/undici/undici:13185:13\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async #e (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:87:109)","service":"backend"}
{"level":"info","message":"prisma:info Starting a sqlite pool with 41 connections.","service":"backend"}
{"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {\"event\":\"server_boot\",\"distinctId\":\"4828b685-b541-4992-b290-ff6d99330fc4\",\"properties\":{}}","service":"backend"}
{"level":"info","message":"Skipping preloading of AnythingLLMOllama - LLM_PROVIDER is ollama.","service":"backend"}
{"level":"info","message":"\u001b[36m[CommunicationKey]\u001b[0m RSA key pair generated for signed payloads within AnythingLLM services.","service":"backend"}
{"level":"info","message":"\u001b[36m[EncryptionManager]\u001b[0m Loaded existing key & salt for encrypting arbitrary data.","service":"backend"}
{"level":"info","message":"[production] AnythingLLM Standalone Backend listening on port 3001. Network discovery is enabled.","service":"backend"}
{"level":"info","message":"\u001b[36m[BackgroundWorkerService]\u001b[0m Starting...","service":"backend"}
{"level":"info","message":"\u001b[36m[BackgroundWorkerService]\u001b[0m Service started with 1 jobs [\"cleanup-orphan-documents\"]","service":"backend"}
{"level":"info","message":"\u001b[36m[OllamaEmbedder]\u001b[0m initialized with model qwen3-embedding:0.6b-q8_0 at http://**.**********.com. num_ctx: 4096","service":"backend"}
{"level":"info","message":"\u001b[36m[OllamaEmbedder]\u001b[0m initialized with model qwen3-embedding:0.6b-q8_0 at http://**.**********.com. num_ctx: 4096","service":"backend"}
{"level":"info","message":"\u001b[32m[Ollama]\u001b[0m Context windows cached for all models!","service":"backend"}
{"level":"info","message":"\u001b[32m[Ollama]\u001b[0m initialized with\nmodel: qwen3-embedding:0.6b-fp16\nperf: base\nn_ctx: 4096","service":"backend"}
{"level":"info","message":"\u001b[36m[OllamaEmbedder]\u001b[0m Embedding 1 chunks of text with qwen3-embedding:0.6b-q8_0.","service":"backend"}
{"level":"info","message":"\u001b[35m[TokenManager]\u001b[0m Initialized new TokenManager instance for model: qwen3-embedding:0.6b-fp16","service":"backend"}
{"level":"error","message":"ResponseError: model 'qwen3-embedding:0.6b-fp16' not found\n    at checkOk (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:77:9)\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async post (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:141:3)\n    at async Ollama.processStreamableRequest (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:260:25)\n    at async Ga.measureStream (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:21:8939)\n    at async r.streamGetChatCompletion (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:136:2711)\n    at async gx (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:299:3125)\n    at async D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:299:4762","service":"backend"}

collector log:

{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"}
{"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"}
{"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"}
{"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"}
{"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"}
{"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"}
{"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"}
{"level":"info","message":"-- Working CTDI_20251014.txt --","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Input will take too long to encode - estimating","service":"collector"}
{"level":"info","message":"[SUCCESS]: CTDI_20251014.txt converted & ready for embedding.\n","service":"collector"}
{"level":"info","message":"-- Working CTDI_20251015.txt --","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Input will take too long to encode - estimating","service":"collector"}
{"level":"info","message":"[SUCCESS]: CTDI_20251015.txt converted & ready for embedding.\n","service":"collector"}
{"level":"info","message":"-- Working URL https://cloud.tencent.com/developer/article/2414682 => (captureAs: text) --","service":"collector"}
{"level":"info","message":"-- URL determined to be text/html (web) --","service":"collector"}
{"level":"info","message":"Cleaning up request handler for request ID.","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Input will take too long to encode - estimating","service":"collector"}
{"level":"info","message":"[SUCCESS]: URL https://cloud.tencent.com/developer/article/2414682 converted & ready for embedding.\n","service":"collector"}
{"level":"info","message":"-- Working 新文件2.txt --","service":"collector"}
{"level":"info","message":"[SUCCESS]: 新文件2.txt converted & ready for embedding.\n","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"}
{"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"}
{"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"}
{"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"}
{"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"}
{"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"}
{"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"}
{"level":"info","message":"-- Working 新文件2.txt --","service":"collector"}
{"level":"info","message":"[SUCCESS]: 新文件2.txt converted & ready for embedding.\n","service":"collector"}
{"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"}
{"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"}
{"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"}
{"level":"info","message":"-- Working 新文件2.txt --","service":"collector"}
{"level":"info","message":"[SUCCESS]: 新文件2.txt converted & ready for embedding.\n","service":"collector"}
@SKYC829 commented on GitHub (Oct 23, 2025): backend log ``` {"level":"info","message":"\u001b[35m[TokenManager]\u001b[0m Initialized new TokenManager instance for model: gpt-3.5-turbo","service":"backend"} {"level":"info","message":"\u001b[36m[EncryptionManager]\u001b[0m Loaded existing key & salt for encrypting arbitrary data.","service":"backend"} {"level":"info","message":"\u001b[33m[ContextWindowFinder]\u001b[0m Pulling remote model map...","service":"backend"} {"level":"info","message":"\u001b[35m[TokenManager]\u001b[0m Returning existing instance for model: gpt-3.5-turbo","service":"backend"} {"level":"info","message":"\u001b[32m[TELEMETRY ENABLED]\u001b[0m Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM.","service":"backend"} {"level":"info","message":"\u001b[33m[ContextWindowFinder]\u001b[0m Error syncing remote model map TypeError: fetch failed\n at node:internal/deps/undici/undici:13185:13\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async #e (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:87:109)","service":"backend"} {"level":"info","message":"prisma:info Starting a sqlite pool with 41 connections.","service":"backend"} {"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {\"event\":\"server_boot\",\"distinctId\":\"4828b685-b541-4992-b290-ff6d99330fc4\",\"properties\":{}}","service":"backend"} {"level":"info","message":"Skipping preloading of AnythingLLMOllama - LLM_PROVIDER is ollama.","service":"backend"} {"level":"info","message":"\u001b[36m[CommunicationKey]\u001b[0m RSA key pair generated for signed payloads within AnythingLLM services.","service":"backend"} {"level":"info","message":"\u001b[36m[EncryptionManager]\u001b[0m Loaded existing key & salt for encrypting arbitrary data.","service":"backend"} {"level":"info","message":"[production] AnythingLLM Standalone Backend listening on port 3001. Network discovery is enabled.","service":"backend"} {"level":"info","message":"\u001b[36m[BackgroundWorkerService]\u001b[0m Starting...","service":"backend"} {"level":"info","message":"\u001b[36m[BackgroundWorkerService]\u001b[0m Service started with 1 jobs [\"cleanup-orphan-documents\"]","service":"backend"} {"level":"info","message":"\u001b[36m[OllamaEmbedder]\u001b[0m initialized with model qwen3-embedding:0.6b-q8_0 at http://**.**********.com. num_ctx: 4096","service":"backend"} {"level":"info","message":"\u001b[36m[OllamaEmbedder]\u001b[0m initialized with model qwen3-embedding:0.6b-q8_0 at http://**.**********.com. num_ctx: 4096","service":"backend"} {"level":"info","message":"\u001b[32m[Ollama]\u001b[0m Context windows cached for all models!","service":"backend"} {"level":"info","message":"\u001b[32m[Ollama]\u001b[0m initialized with\nmodel: qwen3-embedding:0.6b-fp16\nperf: base\nn_ctx: 4096","service":"backend"} {"level":"info","message":"\u001b[36m[OllamaEmbedder]\u001b[0m Embedding 1 chunks of text with qwen3-embedding:0.6b-q8_0.","service":"backend"} {"level":"info","message":"\u001b[35m[TokenManager]\u001b[0m Initialized new TokenManager instance for model: qwen3-embedding:0.6b-fp16","service":"backend"} {"level":"error","message":"ResponseError: model 'qwen3-embedding:0.6b-fp16' not found\n at checkOk (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:77:9)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async post (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:141:3)\n at async Ollama.processStreamableRequest (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:260:25)\n at async Ga.measureStream (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:21:8939)\n at async r.streamGetChatCompletion (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:136:2711)\n at async gx (D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:299:3125)\n at async D:\\AnytgingLLM\\AnythingLLM\\resources\\backend\\server.js:299:4762","service":"backend"} ``` collector log: ``` {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"} {"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"} {"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"} {"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"} {"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"} {"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"} {"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"} {"level":"info","message":"-- Working CTDI_20251014.txt --","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Input will take too long to encode - estimating","service":"collector"} {"level":"info","message":"[SUCCESS]: CTDI_20251014.txt converted & ready for embedding.\n","service":"collector"} {"level":"info","message":"-- Working CTDI_20251015.txt --","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Input will take too long to encode - estimating","service":"collector"} {"level":"info","message":"[SUCCESS]: CTDI_20251015.txt converted & ready for embedding.\n","service":"collector"} {"level":"info","message":"-- Working URL https://cloud.tencent.com/developer/article/2414682 => (captureAs: text) --","service":"collector"} {"level":"info","message":"-- URL determined to be text/html (web) --","service":"collector"} {"level":"info","message":"Cleaning up request handler for request ID.","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Input will take too long to encode - estimating","service":"collector"} {"level":"info","message":"[SUCCESS]: URL https://cloud.tencent.com/developer/article/2414682 converted & ready for embedding.\n","service":"collector"} {"level":"info","message":"-- Working 新文件2.txt --","service":"collector"} {"level":"info","message":"[SUCCESS]: 新文件2.txt converted & ready for embedding.\n","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"} {"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"} {"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"} {"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"} {"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"} {"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"} {"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"} {"level":"info","message":"-- Working 新文件2.txt --","service":"collector"} {"level":"info","message":"[SUCCESS]: 新文件2.txt converted & ready for embedding.\n","service":"collector"} {"level":"info","message":"\u001b[35m[TikTokenTokenizer]\u001b[0m Initialized new TikTokenTokenizer instance.","service":"collector"} {"level":"info","message":"Collector hot directory and tmp storage wiped!","service":"collector"} {"level":"info","message":"[production] AnythingLLM Standalone Document processor listening on port 8888.","service":"collector"} {"level":"info","message":"-- Working 新文件2.txt --","service":"collector"} {"level":"info","message":"[SUCCESS]: 新文件2.txt converted & ready for embedding.\n","service":"collector"} ```
yindo commented 2026-02-22 18:31:46 -05:00
Author
Owner
Copy Link
Copy Source

@SKYC829 commented on GitHub (Oct 23, 2025):

It seems that when switching models, the .env file did not trigger any modifications.

# Auto-dump ENV from system call on 15:24:50 GMT+0800 (中国标准时间)
LLM_PROVIDER='ollama'
EMBEDDING_MODEL_PREF='qwen3-embedding:0.6b-q8_0'
OLLAMA_BASE_PATH='http://*.***.**'
OLLAMA_MODEL_PREF='qwen3-embedding:0.6b-fp16'
OLLAMA_PERFORMANCE_MODE='base'
OLLAMA_KEEP_ALIVE_TIMEOUT='0'
EMBEDDING_ENGINE='ollama'
EMBEDDING_BASE_PATH='http://*.***.**'
EMBEDDING_MODEL_MAX_CHUNK_LENGTH='4096'
VECTOR_DB='milvus'
MILVUS_ADDRESS='http://*.***.**:19530'
MILVUS_USERNAME='root'
MILVUS_PASSWORD='Milvus'
WHISPER_PROVIDER='local'
WHISPER_MODEL_PREF='Xenova/whisper-large'
APP_DISCOVERABLE='true'
TTS_PROVIDER='piper_local'
TTS_PIPER_VOICE_MODEL='zh_CN-huayan-medium'
COMMUNITY_HUB_BUNDLE_DOWNLOADS_ENABLED='allow_all'
STORAGE_DIR='C:\Users\dell\AppData\Roaming\anythingllm-desktop\storage'
SERVER_PORT='3001'
COLLECTOR_PORT='8888'
SIG_KEY='64fb85f6e48b3c122f5f3edca0c9447d868899f936db5d0a54d21648cedca058'
SIG_SALT='6e47df95acabe7e3db872de1b2cada8a2a8682198cf47de6c04b562f83b419aa'

And it seems that the UI rendering has taken up an excessive amount of time. Ollama has already returned the result, but the UI still needs a long time to display.

Image

@SKYC829 commented on GitHub (Oct 23, 2025): It seems that when switching models, the .env file did not trigger any modifications. ``` # Auto-dump ENV from system call on 15:24:50 GMT+0800 (中国标准时间) LLM_PROVIDER='ollama' EMBEDDING_MODEL_PREF='qwen3-embedding:0.6b-q8_0' OLLAMA_BASE_PATH='http://*.***.**' OLLAMA_MODEL_PREF='qwen3-embedding:0.6b-fp16' OLLAMA_PERFORMANCE_MODE='base' OLLAMA_KEEP_ALIVE_TIMEOUT='0' EMBEDDING_ENGINE='ollama' EMBEDDING_BASE_PATH='http://*.***.**' EMBEDDING_MODEL_MAX_CHUNK_LENGTH='4096' VECTOR_DB='milvus' MILVUS_ADDRESS='http://*.***.**:19530' MILVUS_USERNAME='root' MILVUS_PASSWORD='Milvus' WHISPER_PROVIDER='local' WHISPER_MODEL_PREF='Xenova/whisper-large' APP_DISCOVERABLE='true' TTS_PROVIDER='piper_local' TTS_PIPER_VOICE_MODEL='zh_CN-huayan-medium' COMMUNITY_HUB_BUNDLE_DOWNLOADS_ENABLED='allow_all' STORAGE_DIR='C:\Users\dell\AppData\Roaming\anythingllm-desktop\storage' SERVER_PORT='3001' COLLECTOR_PORT='8888' SIG_KEY='64fb85f6e48b3c122f5f3edca0c9447d868899f936db5d0a54d21648cedca058' SIG_SALT='6e47df95acabe7e3db872de1b2cada8a2a8682198cf47de6c04b562f83b419aa' ``` And it seems that the UI rendering has taken up an excessive amount of time. Ollama has already returned the result, but the UI still needs a long time to display. ![Image](https://github.com/user-attachments/assets/0fc52225-d9d5-4d30-8a64-25b8d8b6d212)
yindo commented 2026-02-22 18:31:46 -05:00
Author
Owner
Copy Link
Copy Source

@shatfield4 commented on GitHub (Oct 23, 2025):

The reason the env is not updating for you is because when you change the model via the workspace settings like you show there, that is setting the workspace LLM model so that it is tied to the workspace (and stored in the database not the env).

You will want to set the model in here and make sure to press save so that the global LLM model is set.

Image

The other issue you explained is because when you are deleting models when testing another one and you set the workspace LLM provider on the chat page, it is setting the workspace model only (storing in database not env). What you need to do is update the global model again like in the screenshot above.

If you are constantly downloading and deleting models in between chats, I recommend that you only change the global LLM model. Once you have a few that you are happy with, then use the workspace model switcher to switch between downloaded models.

@shatfield4 commented on GitHub (Oct 23, 2025): The reason the env is not updating for you is because when you change the model via the workspace settings like you show there, that is setting the workspace LLM model so that it is tied to the workspace (and stored in the database not the env). You will want to set the model in here and make sure to press save so that the global LLM model is set. <img width="1422" height="894" alt="Image" src="https://github.com/user-attachments/assets/eda8b5b1-facf-412f-a4fc-b0df11b920cd" /> The other issue you explained is because when you are deleting models when testing another one and you set the workspace LLM provider on the chat page, it is setting the workspace model only (storing in database not env). What you need to do is update the global model again like in the screenshot above. If you are constantly downloading and deleting models in between chats, I recommend that you only change the global LLM model. Once you have a few that you are happy with, then use the workspace model switcher to switch between downloaded models.
yindo changed title from [BUG]: I don't know why I would use an non-existent model to [GH-ISSUE #4574] [BUG]: I don't know why I would use an non-existent model 2026-06-05 14:49:13 -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#2907
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?