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 #688] [API]: Support raw text + metadata uploads #394

New Issue
Closed
opened 2026-02-22 18:19:17 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:19:17 -05:00
Owner
Copy Link
Copy Source

Originally created by @timothycarambat on GitHub (Feb 7, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/688

What would you like to see?

Currently, we support the uploading of documents and links via the collector endpoints in the API. There is a use case though for an API user to directly send raw text and preferred metadata directly to the collector for it to then format and save.

note the metadata cannot allow arbitrary key values or else database schemas for many vector dbs will prevent the upsert as sometimes the metadata is spread into columns and the columns must be homogenous across that collection.

Originally created by @timothycarambat on GitHub (Feb 7, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/688 ### What would you like to see? Currently, we support the uploading of documents and links via the collector endpoints in the API. There is a use case though for an API user to directly send raw text and preferred metadata directly to the collector for it to then format and save. *note* the metadata cannot allow arbitrary key values or else database schemas for many vector dbs will prevent the upsert as sometimes the metadata is spread into columns and the columns must be homogenous across that collection.
yindo added the enhancementfeature request labels 2026-02-22 18:19:17 -05:00
yindo closed this issue 2026-02-22 18:19:18 -05:00
yindo commented 2026-02-22 18:19:18 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 7, 2024):

@icsy7867 - merged

@timothycarambat commented on GitHub (Feb 7, 2024): @icsy7867 - merged
yindo commented 2026-02-22 18:19:18 -05:00
Author
Owner
Copy Link
Copy Source

@icsy7867 commented on GitHub (Feb 7, 2024):

This looks great! Looking at th swagger right now:

{
  "textContent": "This is the raw text that will be saved as a document in AnythingLLM.",
  "metadata": {
    "keyOne": "valueOne",
    "keyTwo": "valueTwo",
    "etc": "etc"
  }
}

For the metadata bits - Can I set any field from the return response? I.E url, docAuthor, title, published etc...?

{
  "success": true,
  "error": null,
  "documents": [
    {
      "id": "c530dbe6-bff1-4b9e-b87f-710d539d20bc",
      "url": "file://my-document.txt",
      "title": "hello-world.txt",
      "docAuthor": "no author found",
      "description": "No description found.",
      "docSource": "My custom description set during upload",
      "chunkSource": "no chunk source specified",
      "published": "1/16/2024, 3:46:33 PM",
      "wordCount": 252,
      "pageContent": "AnythingLLM is the best....",
      "token_count_estimate": 447,
      "location": "custom-documents/raw-my-doc-text-c530dbe6-bff1-4b9e-b87f-710d539d20bc.json"
    }
  ]
}

For my specific use case - I want to specify a URL that will possibly show up here once this is implemented!
https://github.com/Mintplex-Labs/anything-llm/issues/689

Super excited about this!

@icsy7867 commented on GitHub (Feb 7, 2024): This looks great! Looking at th swagger right now: ``` { "textContent": "This is the raw text that will be saved as a document in AnythingLLM.", "metadata": { "keyOne": "valueOne", "keyTwo": "valueTwo", "etc": "etc" } } ``` For the metadata bits - Can I set any field from the return response? I.E url, docAuthor, title, published etc...? ``` { "success": true, "error": null, "documents": [ { "id": "c530dbe6-bff1-4b9e-b87f-710d539d20bc", "url": "file://my-document.txt", "title": "hello-world.txt", "docAuthor": "no author found", "description": "No description found.", "docSource": "My custom description set during upload", "chunkSource": "no chunk source specified", "published": "1/16/2024, 3:46:33 PM", "wordCount": 252, "pageContent": "AnythingLLM is the best....", "token_count_estimate": 447, "location": "custom-documents/raw-my-doc-text-c530dbe6-bff1-4b9e-b87f-710d539d20bc.json" } ] } ``` For my specific use case - I want to specify a URL that will possibly show up here once this is implemented! https://github.com/Mintplex-Labs/anything-llm/issues/689 Super excited about this!
yindo commented 2026-02-22 18:19:18 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 8, 2024):

@icsy7867 In that case, you can specify any of the fields from the /api/v1/document/metadata-schema endpoint. You can override the url metadata and the link will be present, but that won't appear in the UI until #689 is merged - so id wait for that first!

@timothycarambat commented on GitHub (Feb 8, 2024): @icsy7867 In that case, you can specify any of the fields from the `/api/v1/document/metadata-schema` endpoint. You can override the `url` metadata and the link will be present, but that won't appear in the UI until #689 is merged - so id wait for that first!
yindo changed title from [API]: Support raw text + metadata uploads to [GH-ISSUE #688] [API]: Support raw text + metadata uploads 2026-06-05 14:35:05 -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 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#394
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?