apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-06-25 08:48:13 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add MiniMax provider support (Chat + TTS) (#309)

Browse source 
* feat: add MiniMax provider support (Chat + TTS)

- Add MiniMax LLM provider using OpenAI-compatible API
  - Models: MiniMax-M2.7, MiniMax-M2.7-highspeed
  - Default base URL: https://api.minimax.io/v1
  - Uses MINIMAX_API_KEY for authentication
- Add MiniMax TTS provider using Pipecat's MiniMaxHttpTTSService
  - Models: speech-2.8-hd (default), speech-2.8-turbo
  - 6 built-in voices
  - Requires group_id configuration
- Add unit tests for both providers

* fix(minimax): validator, temperature, session cleanup, reasoning filter
  - check_validity.py: wire MiniMax into _validator_map and enforce
    group_id at save time. Without this, saving a config with a valid
    key was rejected.
  - registry.py: surface temperature on the LLM config (gt=0; MiniMax
    rejects 0) and base_url on the TTS config
  - service_factory.py:
    * Plumb temperature through create_llm_service
    * Normalize TTS base_url to include /t2a_v2 — pipecat appends only
      ?GroupId=... to the URL.
    * Use the new MiniMaxLLMService (from pipecat) to strip
      <think>...</think> reasoning that MiniMax-M2.7 emits inline in
      delta.content (otherwise it leaks straight to TTS).
    * Use MiniMaxOwnedSessionTTSService so the per-instance aiohttp
      session gets closed in cleanup() instead of leaking sockets/FDs.
  - minimax_tts.py: small wrapper around MiniMaxHttpTTSService that owns
    the session it was handed (pipecat's caller-owns-session API
    conflicts with the ftory's per-instance pattern).
  - pipecat submodule: bumps to a commit that adds MiniMaxLLMService — a
    thin OpenAILLMService subclass with the streaming <think> filter
    (mirrors NvidiaLLMService's pattern for NIM reasoning models).
  - Tests updated/added for all of the above.

  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: octo-patch <octo-patch@github.com>
Co-authored-by: Sabiha Khan <sabihak89@gmail.com>
This commit is contained in:
Octopus 2026-05-22 15:39:41 +08:00 • committed by GitHub
parent 38c2003734
commit 0e0d3136ca
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 291 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

19
api/services/configuration/check_validity.py
View file

@ -53,6 +53,7 @@ class UserConfigurationValidator:
ServiceProviders.ASSEMBLYAI.value: self._check_assemblyai_api_key,
ServiceProviders.GLADIA.value: self._check_gladia_api_key,
ServiceProviders.RIME.value: self._check_rime_api_key,
ServiceProviders.MINIMAX.value: self._check_minimax_api_key,
}
async def validate(
@ -147,6 +148,19 @@ class UserConfigurationValidator:
return [{"model": service_name, "message": str(e)}]
return []
# MiniMax TTS requires a group_id alongside the API key.
# LLM configs don't expose group_id, so only check when the field exists.
if provider == ServiceProviders.MINIMAX.value and hasattr(
service_config, "group_id"
):
if not getattr(service_config, "group_id", None):
return [
{
"model": service_name,
"message": "group_id is required for MiniMax TTS",
}
]
api_key = service_config.api_key
try:
@ -253,3 +267,8 @@ class UserConfigurationValidator:
def _check_rime_api_key(self, model: str, api_key: str) -> bool:
return True
def _check_minimax_api_key(self, model: str, api_key: str) -> bool:
# MiniMax doesn't publish a cheap key-validation endpoint; trust the key
# at save time and surface auth errors at first call (same as Rime/Sarvam).
return True