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 #2450] [FEAT]: Support @agent from API OpenAI Compatible endpoints #1591

New Issue
Closed
opened 2026-02-22 18:25:34 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:25:34 -05:00
Owner
Copy Link
Copy Source

Originally created by @amengus87 on GitHub (Oct 9, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2450

Originally assigned to: @timothycarambat on GitHub.

How are you running AnythingLLM?

Docker (local)

What happened?

Hello AnythingLLM Team 👋
Awesome product you have done!

I'm encountering an issue about requesting @agentfrom OpenAI compatible endpoint (/v1/openai/chat/completions) => Agent is not triggered

How can we use @agentfeature inside OpenAI compatible endpoints from the AnythingLLM API?

Are there known steps to reproduce?

Working (using /v1/workspace/{slug}/thread/{threadSlug}/stream-chat endpoint)

import requests

url = 'http://localhost:3001/api/v1/workspace/internet-knowledge/thread/adc71dbd-5850-4a5e-aad0-7494da39b2cc/stream-chat'

headers = {
    'accept': 'text/event-stream',
    'Authorization': 'Bearer 00000000-0000-0000-0000-000000000000',
    'Content-Type': 'application/json',
}

data = {
    "message": "@agent Extract links of http://anythingllm.com",
    "mode": "chat",
    "userId": 1
}

response = requests.post(url, headers=headers, json=data)

print(response.text)

data: {"id":"05f1ab51-9965-4457-b11a-0e9f5d902b32","type":"agentThought","thought":"@agent: Scraping the content of http://anythingllm.com/","sources":[],"attachments":[],"close":false,"error":null}

data: {"id":"05f1ab51-9965-4457-b11a-0e9f5d902b32","type":"textResponse","textResponse":"Here are some of the main links from the AnythingLLM webpage:\n\n1. AnythingLLM Cloud: Link\n2. Docs: Link\n3](https://docs.anythingllm.com/)/n3). Github: Link\n4](https://github.com/Mintplex-Labs/anything-llm)/n4). Download AnythingLLM: Link\n\nAdditionally, the webpage includes links to their social media profiles and contact pages, such as their Twitter, Discord, and a contact email address.","sources":[],"attachments":[],"close":true,"error":null}

data: {"uuid":"05f1ab51-9965-4457-b11a-0e9f5d902b32","type":"finalizeResponseStream","textResponse":"Here are some of the main links from the AnythingLLM webpage:\n\n1. AnythingLLM Cloud: Link\n2. Docs: Link\n3](https://docs.anythingllm.com/)/n3). Github: Link\n4](https://github.com/Mintplex-Labs/anything-llm)/n4). Download AnythingLLM: Link\n\nAdditionally, the webpage includes links to their social media profiles and contact pages, such as their Twitter, Discord, and a contact email address.","thoughts":["@agent: Scraping the content of http://anythingllm.com/"],"close":true,"error":false}

Not working (using /v1/openai/chat/completions endpoint)

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model_name="internet-knowledge",
    openai_api_key="00000000-0000-0000-0000-000000000000",
    openai_api_base="http://localhost:3001/api/v1/openai",
    default_headers={
        "Authorization": "Bearer 00000000-0000-0000-0000-000000000000",
        "Accept": "*/*",
        "Content-Type": "application/json"
    }
)

messages = [
    ("human", "@agent Extract links of http://anythingllm.com"),
]
for chunk in llm.stream(messages):
    print(chunk.content, end="")

I'm unable to extract links from specific websites like http://anythingllm.com/. You may visit the website directly and browse through it for any links or resources you need.

Originally created by @amengus87 on GitHub (Oct 9, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2450 Originally assigned to: @timothycarambat on GitHub. ### How are you running AnythingLLM? Docker (local) ### What happened? Hello AnythingLLM Team 👋 Awesome product you have done! I'm encountering an issue about requesting `@agent`from OpenAI compatible endpoint (/v1/openai/chat/completions) => Agent is not triggered How can we use `@agent`feature inside OpenAI compatible endpoints from the AnythingLLM API? ### Are there known steps to reproduce? # Working (using /v1/workspace/{slug}/thread/{threadSlug}/stream-chat endpoint) ```python import requests url = 'http://localhost:3001/api/v1/workspace/internet-knowledge/thread/adc71dbd-5850-4a5e-aad0-7494da39b2cc/stream-chat' headers = { 'accept': 'text/event-stream', 'Authorization': 'Bearer 00000000-0000-0000-0000-000000000000', 'Content-Type': 'application/json', } data = { "message": "@agent Extract links of http://anythingllm.com", "mode": "chat", "userId": 1 } response = requests.post(url, headers=headers, json=data) print(response.text) ``` > data: {"id":"05f1ab51-9965-4457-b11a-0e9f5d902b32","type":"agentThought","thought":"@agent: Scraping the content of http://anythingllm.com/","sources":[],"attachments":[],"close":false,"error":null} > > data: {"id":"05f1ab51-9965-4457-b11a-0e9f5d902b32","type":"textResponse","textResponse":"Here are some of the main links from the AnythingLLM webpage:\n\n1. **AnythingLLM Cloud**: [Link](https://my.mintplexlabs.com/aio-checkout?product=anythingllm)\n2. **Docs**: [Link]([https://docs.anythingllm.com/)\n3](https://docs.anythingllm.com/)/n3). **Github**: [Link]([https://github.com/Mintplex-Labs/anything-llm)\n4](https://github.com/Mintplex-Labs/anything-llm)/n4). **Download AnythingLLM**: [Link](https://my.mintplexlabs.com/aio-checkout?product=anythingllm)\n\nAdditionally, the webpage includes links to their social media profiles and contact pages, such as their Twitter, Discord, and a contact email address.","sources":[],"attachments":[],"close":true,"error":null} > > data: {"uuid":"05f1ab51-9965-4457-b11a-0e9f5d902b32","type":"finalizeResponseStream","textResponse":"Here are some of the main links from the AnythingLLM webpage:\n\n1. **AnythingLLM Cloud**: [Link](https://my.mintplexlabs.com/aio-checkout?product=anythingllm)\n2. **Docs**: [Link]([https://docs.anythingllm.com/)\n3](https://docs.anythingllm.com/)/n3). **Github**: [Link]([https://github.com/Mintplex-Labs/anything-llm)\n4](https://github.com/Mintplex-Labs/anything-llm)/n4). **Download AnythingLLM**: [Link](https://my.mintplexlabs.com/aio-checkout?product=anythingllm)\n\nAdditionally, the webpage includes links to their social media profiles and contact pages, such as their Twitter, Discord, and a contact email address.","thoughts":["@agent: Scraping the content of http://anythingllm.com/"],"close":true,"error":false} # Not working (using /v1/openai/chat/completions endpoint) ```python from langchain_openai import ChatOpenAI llm = ChatOpenAI( model_name="internet-knowledge", openai_api_key="00000000-0000-0000-0000-000000000000", openai_api_base="http://localhost:3001/api/v1/openai", default_headers={ "Authorization": "Bearer 00000000-0000-0000-0000-000000000000", "Accept": "*/*", "Content-Type": "application/json" } ) messages = [ ("human", "@agent Extract links of http://anythingllm.com"), ] for chunk in llm.stream(messages): print(chunk.content, end="") ``` > I'm unable to extract links from specific websites like http://anythingllm.com/. You may visit the website directly and browse through it for any links or resources you need.
yindo added the enhancementfeature request labels 2026-02-22 18:25:34 -05:00
yindo commented 2026-02-22 18:25:34 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Oct 9, 2024):

Ah, yes the /v1/workspace/chat endpoint is the only endpoint that supports that functionality currently. We could expand it to this endpoint as well. Can I understand more about the use case here over needing this functionality vs just using the /workspace/chat endpoint?

We would ideally not mess with the "compatible" part of OpenAI compatible too much, but I'm no opposed to it right now

@timothycarambat commented on GitHub (Oct 9, 2024): Ah, yes the `/v1/workspace/chat` endpoint is the only endpoint that supports that functionality currently. We could expand it to this endpoint as well. Can I understand more about the use case here over needing this functionality vs just using the /workspace/chat endpoint? We would ideally not mess with the "compatible" part of OpenAI compatible too much, but I'm no opposed to it right now
yindo commented 2026-02-22 18:25:34 -05:00
Author
Owner
Copy Link
Copy Source

@amengus87 commented on GitHub (Oct 11, 2024):

Ah, yes the /v1/workspace/chat endpoint is the only endpoint that supports that functionality currently

Good to know, thank you!

Can I understand more about the use case here over needing this functionality vs just using the /workspace/chat endpoint?

We use several native applications (not made by us) in our corp that allow us to change the OpenAI base endpoint URL and we would like to provide the power of @agent from AnythingLLM to them. (We can't use the widget)

@amengus87 commented on GitHub (Oct 11, 2024): > Ah, yes the /v1/workspace/chat endpoint is the only endpoint that supports that functionality currently Good to know, thank you! > Can I understand more about the use case here over needing this functionality vs just using the /workspace/chat endpoint? We use several native applications (not made by us) in our corp that allow us to change the OpenAI base endpoint URL and we would like to provide the power of `@agent` from AnythingLLM to them. (We can't use the widget)
yindo changed title from [FEAT]: Support @agent from API OpenAI Compatible endpoints to [GH-ISSUE #2450] [FEAT]: Support @agent from API OpenAI Compatible endpoints 2026-06-05 14:41:37 -04:00
yindo closed this issue 2026-06-05 14:41:37 -04:00
yindo commented 2026-06-05 14:41:38 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 1, 2026):

This has been supported for several months now 👍

<!-- gh-comment-id:4596677169 --> @timothycarambat commented on GitHub (Jun 1, 2026): This has been supported for several months now 👍
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 enhancement feature request
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#1591
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?