6 views
-/https://github.com/berriai/litellm/issues/29570
GitHub · issue

#29570 [Feature]: Add support for the volcanic ark

  • State: open
  • Author: @jjambo
  • Labels: enhancement, potential-duplicate

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### The Feature

Add support for the volcanic ark doubao-embedding-vision-251215 model

### Motivation, pitch

The closed pure text vectorization model of Volcano Ark only provides this multimodal vectorization model, and the calling method of this model is different from that of text: input=[ {"type": "text", "text": "This painting depicts a serene rural scenery"}, {"type": "image_url", "image_url": {"url": "https://example.com/countryside.jpg"}} ],

### What part of LiteLLM is this about?

_No response_

### LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users?

No

### Twitter / LinkedIn details

_No response_

Open on GitHub

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (5 events)
#0 of 0 · 31d18h57m7s ago — entered · #import:https:::github.com:berriai:litellm post #1918
-/https://github.com/berriai/litellm/issues/29570⭐4:1-/https://github.com/berriai/litellm/issues/31078
29570 requires broader provider integration, multimodal request translation, model registration, and compatibility testing; 31078 is a comparatively localized proxy authorization-path correction.
#0 of 0 · 31d18h47m6s ago · #import:https:::github.com:berriai:litellm post #2091
-/https://github.com/berriai/litellm/issues/29570⭐3:1-/https://github.com/berriai/litellm/issues/26698
The right issue is harder because it requires introducing and validating new provider/model integration, including multimodal request construction, capability mapping, and likely documentation and regression coverage. The left issue is a narrowly scoped transformation correction with localized testing.
#0 of 0 · 31d18h22m13s ago · #import:https:::github.com:berriai:litellm post #2484
-/https://github.com/berriai/litellm/issues/29570⭐4:1-/https://github.com/berriai/litellm/issues/28126
The right issue is harder because it requires introducing and validating a new provider/model integration, including multimodal request handling, configuration, compatibility, and coverage across relevant code paths. The left issue is a localized type-handling fix with a narrowly scoped regression test.
#0 of 0 · 31d18h4m51s ago · #import:https:::github.com:berriai:litellm post #2775
-/https://github.com/berriai/litellm/issues/158613:1-/https://github.com/berriai/litellm/issues/29570⭐
The left issue is harder because it spans several public API routes and requires coordinated routing, authorization, storage semantics, backward compatibility, and broader integration testing. The right issue is comparatively contained within a provider adapter, model registration, request-shape handling, and targeted tests.
#0 of 0 · 31d17h47m4s ago — current · #import:https:::github.com:berriai:litellm post #3092
-/https://github.com/berriai/litellm/issues/187305:1-/https://github.com/berriai/litellm/issues/29570⭐
Concurrent quota enforcement requires race-safe accounting, correct distributed behavior, and regression testing under load; the provider addition is comparatively localized to an adapter, request formatting, and basic validation.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search