dograh/api/services/configuration/check_validity.py

387 lines
16 KiB
Python
Raw Normal View History

from typing import Optional, TypedDict
2025-09-09 14:37:32 +05:30
import openai
2026-03-06 16:49:14 +05:30
from deepgram import DeepgramClient
2025-09-09 14:37:32 +05:30
from groq import Groq
# try:
# from pyneuphonic import Neuphonic
# except ImportError:
# Neuphonic = None
from api.schemas.user_configuration import (
UserConfiguration,
)
from api.services.configuration.registry import ServiceConfig, ServiceProviders
from api.services.mps_service_key_client import mps_service_key_client
from api.utils.url_security import validate_user_configured_service_url
2025-09-09 14:37:32 +05:30
AuthContext = TypedDict(
"AuthContext",
{"organization_id": Optional[int], "created_by": Optional[str]},
total=False,
)
2025-09-09 14:37:32 +05:30
class APIKeyStatus(TypedDict):
model: str
message: str
class APIKeyStatusResponse(TypedDict):
status: list[APIKeyStatus]
class UserConfigurationValidator:
def __init__(self):
self._validator_map = {
ServiceProviders.OPENAI.value: self._check_openai_api_key,
ServiceProviders.DEEPGRAM.value: self._check_deepgram_api_key,
ServiceProviders.GROQ.value: self._check_groq_api_key,
2026-02-09 13:31:32 +05:30
ServiceProviders.OPENROUTER.value: self._check_openrouter_api_key,
2025-09-09 14:37:32 +05:30
ServiceProviders.ELEVENLABS.value: self._validate_elevenlabs_api_key,
ServiceProviders.GOOGLE.value: self._check_google_api_key,
ServiceProviders.AZURE.value: self._check_azure_api_key,
ServiceProviders.CARTESIA.value: self._check_cartesia_api_key,
ServiceProviders.DOGRAH.value: self._check_dograh_api_key,
ServiceProviders.SARVAM.value: self._check_sarvam_api_key,
ServiceProviders.SPEECHMATICS.value: self._check_speechmatics_api_key,
ServiceProviders.CAMB.value: self._check_camb_api_key,
2026-03-19 15:06:59 +05:30
ServiceProviders.AWS_BEDROCK.value: self._check_aws_bedrock_api_key,
ServiceProviders.SPEACHES.value: self._check_speaches_api_key,
2026-05-22 18:04:59 +05:30
ServiceProviders.GOOGLE_VERTEX.value: self._check_google_vertex_llm_api_key,
ServiceProviders.OPENAI_REALTIME.value: self._check_openai_api_key,
2026-05-22 18:04:59 +05:30
ServiceProviders.GROK_REALTIME.value: self._check_grok_realtime_api_key,
ServiceProviders.ULTRAVOX_REALTIME.value: self._check_ultravox_realtime_api_key,
ServiceProviders.GOOGLE_REALTIME.value: self._check_google_api_key,
ServiceProviders.GOOGLE_VERTEX_REALTIME.value: self._check_google_vertex_realtime_api_key,
2026-04-03 07:10:37 +05:30
ServiceProviders.ASSEMBLYAI.value: self._check_assemblyai_api_key,
2026-04-04 14:47:48 +05:30
ServiceProviders.GLADIA.value: self._check_gladia_api_key,
2026-04-07 14:05:47 +05:30
ServiceProviders.RIME.value: self._check_rime_api_key,
feat: add MiniMax provider support (Chat + TTS) (#309) * 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>
2026-05-22 15:39:41 +08:00
ServiceProviders.MINIMAX.value: self._check_minimax_api_key,
2025-09-09 14:37:32 +05:30
}
async def validate(
self,
configuration: UserConfiguration,
organization_id: Optional[int] = None,
created_by: Optional[str] = None,
) -> APIKeyStatusResponse:
self._auth_context: AuthContext = {
"organization_id": organization_id,
"created_by": created_by,
}
2025-09-09 14:37:32 +05:30
status_list = []
status_list.extend(self._validate_service(configuration.llm, "llm"))
status_list.extend(self._validate_service(configuration.stt, "stt"))
status_list.extend(self._validate_service(configuration.tts, "tts"))
# Embeddings is optional - only validate if configured
status_list.extend(
self._validate_service(
configuration.embeddings, "embeddings", required=False
)
)
# Realtime is optional - only validate if is_realtime is enabled
if configuration.is_realtime:
status_list.extend(
self._validate_service(
configuration.realtime, "realtime", required=True
)
)
2025-09-09 14:37:32 +05:30
if status_list:
raise ValueError(status_list)
return {"status": [{"model": "all", "message": "ok"}]}
def _validate_service(
self,
service_config: Optional[ServiceConfig],
service_name: str,
required: bool = True,
2025-09-09 14:37:32 +05:30
) -> list[APIKeyStatus]:
"""Validate a service configuration and return any error statuses."""
if not service_config:
if required:
return [{"model": service_name, "message": "API key is missing"}]
return [] # Optional service not configured is OK
2025-09-09 14:37:32 +05:30
provider = service_config.provider
2026-03-19 15:06:59 +05:30
for url_field in ("base_url", "endpoint"):
url = getattr(service_config, url_field, None)
if url:
try:
validate_user_configured_service_url(
url,
field_name=url_field,
)
except ValueError as e:
return [{"model": service_name, "message": str(e)}]
# Speaches doesn't require an API key
if provider == ServiceProviders.SPEACHES.value:
try:
if not self._check_speaches_api_key(provider, service_config):
return [
{
"model": service_name,
"message": f"Invalid {provider} configuration",
}
]
except ValueError as e:
return [{"model": service_name, "message": str(e)}]
return []
# Vertex Realtime uses service-account credentials (or ADC) instead of api_key
if provider == ServiceProviders.GOOGLE_VERTEX_REALTIME.value:
try:
if not self._check_google_vertex_realtime_api_key(
provider, service_config
):
return [
{
"model": service_name,
"message": f"Invalid {provider} configuration",
}
]
except ValueError as e:
return [{"model": service_name, "message": str(e)}]
return []
2026-05-22 18:04:59 +05:30
# Vertex LLM uses service-account credentials (or ADC) instead of api_key
if provider == ServiceProviders.GOOGLE_VERTEX.value:
try:
if not self._check_google_vertex_llm_api_key(provider, service_config):
return [
{
"model": service_name,
"message": f"Invalid {provider} configuration",
}
]
except ValueError as e:
return [{"model": service_name, "message": str(e)}]
return []
2026-03-19 15:06:59 +05:30
# AWS Bedrock uses AWS credentials instead of api_key
if provider == ServiceProviders.AWS_BEDROCK.value:
try:
if not self._check_aws_bedrock_api_key(provider, service_config):
return [
{
"model": service_name,
"message": f"Invalid {provider} credentials",
}
]
except ValueError as e:
return [{"model": service_name, "message": str(e)}]
return []
feat: add MiniMax provider support (Chat + TTS) (#309) * 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>
2026-05-22 15:39:41 +08:00
# 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",
}
]
2025-09-09 14:37:32 +05:30
api_key = service_config.api_key
try:
if not self._check_api_key(provider, api_key, service_config):
return [
{
"model": service_name,
"message": (
f"Invalid {provider} API key. Please verify your API key is "
f"correct, has not expired, and has the required permissions."
),
}
]
except ValueError as e:
return [{"model": service_name, "message": str(e)}]
2025-09-09 14:37:32 +05:30
return []
def _check_api_key(
self,
provider: str,
api_key: str,
service_config: Optional[ServiceConfig] = None,
) -> bool:
2025-09-09 14:37:32 +05:30
"""Check if an API key for a provider is valid."""
validator = self._validator_map.get(provider)
if not validator:
return False
if provider in (
ServiceProviders.OPENAI.value,
ServiceProviders.OPENAI_REALTIME.value,
):
return validator(provider, api_key, service_config)
2025-09-09 14:37:32 +05:30
return validator(provider, api_key)
def _check_openai_api_key(
self, model: str, api_key: str, service_config: Optional[ServiceConfig] = None
) -> bool:
client_kwargs: dict[str, str] = {"api_key": api_key}
base_url = getattr(service_config, "base_url", None) if service_config else None
if base_url:
client_kwargs["base_url"] = base_url
client = openai.OpenAI(**client_kwargs)
2025-09-09 14:37:32 +05:30
try:
client.models.list()
return True
2025-09-09 14:37:32 +05:30
except openai.AuthenticationError:
if base_url and "openai.com" not in base_url:
raise ValueError(
f"Invalid OpenAI API key. The key was rejected by the API at {base_url}. "
"Please check that your API key is correct and has not been revoked."
)
raise ValueError(
"Invalid OpenAI API key. The key was rejected by the OpenAI API. "
"Please check that your API key is correct and has not been revoked. "
"You can verify your keys at https://platform.openai.com/api-keys."
)
except openai.APIConnectionError:
if base_url:
raise ValueError(
f"Could not connect to the OpenAI-compatible API at {base_url}. "
"Please verify that the base_url is correct and reachable, and try again."
)
raise ValueError(
"Could not connect to the OpenAI API. Please check your network connection "
"and try again."
)
except openai.APIError:
if base_url:
raise ValueError(
f"The OpenAI-compatible API at {base_url} returned an error while "
"validating the API key. Please verify that the base_url is correct, "
"the service is available, and the API key is valid."
)
raise ValueError(
"The OpenAI API returned an error while validating the API key. "
"Please try again later."
)
except Exception:
if base_url:
raise ValueError(
f"Failed to validate the OpenAI API key using the API at {base_url}. "
"Please verify that the base_url is correct and reachable, and that the "
"API key is valid."
)
raise ValueError(
"Failed to validate the OpenAI API key. Please try again later."
)
2025-09-09 14:37:32 +05:30
def _check_deepgram_api_key(self, model: str, api_key: str) -> bool:
try:
2026-03-06 16:49:14 +05:30
deepgram = DeepgramClient(api_key=api_key)
deepgram.manage.v1.projects.list()
return True
2026-03-06 16:49:14 +05:30
except Exception:
raise ValueError(
"Invalid Deepgram API key. The key was rejected by the Deepgram API. "
"Please check that your API key is correct and active. "
"You can verify your keys at https://console.deepgram.com/."
)
2025-09-09 14:37:32 +05:30
def _check_groq_api_key(self, model: str, api_key: str) -> bool:
client = Groq(api_key=api_key)
try:
client.models.list()
return True
2025-09-09 14:37:32 +05:30
except Exception:
raise ValueError(
"Invalid Groq API key. The key was rejected by the Groq API. "
"Please check that your API key is correct and active. "
"You can verify your keys at https://console.groq.com/keys."
)
2025-09-09 14:37:32 +05:30
def _validate_elevenlabs_api_key(self, model: str, api_key: str) -> bool:
return True
def _check_google_api_key(self, model: str, api_key: str) -> bool:
return True
def _check_azure_api_key(self, model: str, api_key: str) -> bool:
return True
def _check_cartesia_api_key(self, model: str, api_key: str) -> bool:
return True
def _check_dograh_api_key(self, model: str, api_key: str) -> bool:
if api_key.startswith("dgr"):
raise ValueError(
"You provided a Dograh API key (dgr...) instead of a service key. "
"Please use a service key (mps...)."
)
auth = getattr(self, "_auth_context", {})
return mps_service_key_client.validate_service_key(
api_key,
organization_id=auth.get("organization_id"),
created_by=auth.get("created_by"),
)
2025-09-09 14:37:32 +05:30
def _check_sarvam_api_key(self, model: str, api_key: str) -> bool:
return True
2026-02-09 13:31:32 +05:30
def _check_openrouter_api_key(self, model: str, api_key: str) -> bool:
return True
2026-05-22 18:04:59 +05:30
def _check_grok_realtime_api_key(self, model: str, api_key: str) -> bool:
return True
def _check_ultravox_realtime_api_key(self, model: str, api_key: str) -> bool:
2026-05-22 18:04:59 +05:30
return True
def _check_speechmatics_api_key(self, model: str, api_key: str) -> bool:
return True
2026-03-19 15:06:59 +05:30
def _check_camb_api_key(self, model: str, api_key: str) -> bool:
return True
def _check_speaches_api_key(self, model: str, service_config) -> bool:
if not getattr(service_config, "base_url", None):
raise ValueError("base_url is required for Speaches services")
return True
def _check_google_vertex_realtime_api_key(self, model: str, service_config) -> bool:
if not getattr(service_config, "project_id", None):
raise ValueError("project_id is required for Google Vertex Realtime")
if not getattr(service_config, "location", None):
raise ValueError("location is required for Google Vertex Realtime")
return True
2026-05-22 18:04:59 +05:30
def _check_google_vertex_llm_api_key(self, model: str, service_config) -> bool:
if not getattr(service_config, "project_id", None):
raise ValueError("project_id is required for Google Vertex")
if not getattr(service_config, "location", None):
raise ValueError("location is required for Google Vertex")
return True
2026-03-19 15:06:59 +05:30
def _check_aws_bedrock_api_key(self, model: str, service_config) -> bool:
if not service_config.aws_access_key or not service_config.aws_secret_key:
raise ValueError("AWS access key and secret key are required for Bedrock")
return True
2026-04-03 07:10:37 +05:30
def _check_assemblyai_api_key(self, model: str, service_config) -> bool:
return True
2026-04-04 14:47:48 +05:30
def _check_gladia_api_key(self, model: str, api_key: str) -> bool:
return True
2026-04-07 14:05:47 +05:30
def _check_rime_api_key(self, model: str, api_key: str) -> bool:
return True
feat: add MiniMax provider support (Chat + TTS) (#309) * 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>
2026-05-22 15:39:41 +08:00
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