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 #3125] [BUG]: Agent not working - FETCH FAILED error #2007

New Issue
Closed
opened 2026-02-22 18:27:43 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:27:43 -05:00
Owner
Copy Link
Copy Source

Originally created by @emad-qadri on GitHub (Feb 5, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3125

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I thoroughly reviewed the past related issue - https://github.com/Mintplex-Labs/anything-llm/issues/1608 but didn't find any resolution.

I have already testing manually communicating with Ollama, it works completely fine. See screenshot. So, Ollama is NOT the problem. AnythingLLM seems to fail to communicate with Ollama. Could it be that for Agents to work properly; the default AnythingLLM Embedder should be used?

I am using ":llama3:8b-instruct-q8_0" as Agent LLM model.

{"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - sent_chat","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Start 14d3a948-d52b-4958-996b-2cb2fab70dde::ollama:llama3:8b-instruct-q8_0","service":"backend"}
{"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {"event":"agent_chat_started","distinctId":"4dd208d1-fca3-4021-bc4d-3503352ebefb","properties":{"runtime":"desktop"}}","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached websocket plugin to Agent cluster","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached chat-history plugin to Agent cluster","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attaching user and default agent to Agent cluster.","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached rag-memory plugin to Agent cluster","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached document-summarizer plugin to Agent cluster","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached web-scraping plugin to Agent cluster","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached save-file-to-browser plugin to Agent cluster","service":"backend"}
{"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached create-chart plugin to Agent cluster","service":"backend"}
{"level":"info","message":"\u001b[36m[NativeEmbedder]\u001b[0m Initialized","service":"backend"}
{"level":"error","message":"fetch failed TypeError: fetch failed\n at Object.fetch (node:internal/deps/undici/undici:11457:11)\n at async post (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\node_modules\ollama\dist\browser.cjs:114:20)\n at async Ollama.processStreamableRequest (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\node_modules\ollama\dist\browser.cjs:252:22)\n at async #e (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\server.js:255:2228)\n at async Oi.functionCall (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\server.js:241:931)\n at async Oi.complete (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\server.js:255:2404)\n at async Xi.handleExecution (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\server.js:274:406)\n at async Xi.reply (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\server.js:274:274)\n at async Xi.chat (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\server.js:255:32084)\n at async Xi.start (C:\Users\emadq\AppData\Local\Programs\AnythingLLM\resources\backend\server.js:255:31518)","service":"backend"}

Image

Are there known steps to reproduce?

No response

Originally created by @emad-qadri on GitHub (Feb 5, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3125 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I thoroughly reviewed the past related issue - https://github.com/Mintplex-Labs/anything-llm/issues/1608 but didn't find any resolution. I have already testing manually communicating with Ollama, it works completely fine. See screenshot. So, Ollama is NOT the problem. AnythingLLM seems to fail to communicate with Ollama. Could it be that for Agents to work properly; the default AnythingLLM Embedder should be used? I am using ":llama3:8b-instruct-q8_0" as Agent LLM model. {"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - sent_chat","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Start 14d3a948-d52b-4958-996b-2cb2fab70dde::ollama:llama3:8b-instruct-q8_0","service":"backend"} {"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {\"event\":\"agent_chat_started\",\"distinctId\":\"4dd208d1-fca3-4021-bc4d-3503352ebefb\",\"properties\":{\"runtime\":\"desktop\"}}","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached websocket plugin to Agent cluster","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached chat-history plugin to Agent cluster","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attaching user and default agent to Agent cluster.","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached rag-memory plugin to Agent cluster","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached document-summarizer plugin to Agent cluster","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached web-scraping plugin to Agent cluster","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached save-file-to-browser plugin to Agent cluster","service":"backend"} {"level":"info","message":"\u001b[36m[AgentHandler]\u001b[0m Attached create-chart plugin to Agent cluster","service":"backend"} {"level":"info","message":"\u001b[36m[NativeEmbedder]\u001b[0m Initialized","service":"backend"} {"level":"error","message":"fetch failed TypeError: fetch failed\n at Object.fetch (node:internal/deps/undici/undici:11457:11)\n at async post (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:114:20)\n at async Ollama.processStreamableRequest (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\node_modules\\ollama\\dist\\browser.cjs:252:22)\n at async #e (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\server.js:255:2228)\n at async Oi.functionCall (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\server.js:241:931)\n at async Oi.complete (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\server.js:255:2404)\n at async Xi.handleExecution (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\server.js:274:406)\n at async Xi.reply (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\server.js:274:274)\n at async Xi.chat (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\server.js:255:32084)\n at async Xi.start (C:\\Users\\emadq\\AppData\\Local\\Programs\\AnythingLLM\\resources\\backend\\server.js:255:31518)","service":"backend"} ![Image](https://github.com/user-attachments/assets/6145534b-37f5-40b8-ba23-d4a072602d36) ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:27:43 -05:00
yindo closed this issue 2026-02-22 18:27:43 -05:00
yindo commented 2026-02-22 18:27:43 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 5, 2025):

With the same model I am unable to replicate. That PS shows you using the REST API. What base URL are you using in AnythingLLM to reach the Ollama instance. You should see models in the dropdown and everything.

If we can fetch the models, we can run agents, and we can send chats. All are using the same base URL

@timothycarambat commented on GitHub (Feb 5, 2025): With the same model I am unable to replicate. That PS shows you using the REST API. What base URL are you using in AnythingLLM to reach the Ollama instance. You should see models in the dropdown and everything. If we can fetch the models, we can run agents, and we can send chats. All are using the same base URL
yindo changed title from [BUG]: Agent not working - FETCH FAILED error to [GH-ISSUE #3125] [BUG]: Agent not working - FETCH FAILED error 2026-06-05 14:43:59 -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#2007
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?