10563900a3
- Add multi-provider LLM architecture supporting OpenRouter, OpenAI, Gemini, and custom providers - Implement global LLM on/off switch with default DISABLED state for cost protection - Add per-character LLM configuration with provider-specific models and settings - Create performance-optimized caching system for LLM enabled status checks - Add API key validation before enabling LLM providers to prevent broken configurations - Implement audit logging for all LLM enable/disable actions for cost accountability - Create comprehensive admin UI with prominent cost warnings and confirmation dialogs - Add visual indicators in character list for custom AI model configurations - Build character-specific LLM client system with global fallback mechanism - Add database schema support for per-character LLM settings - Implement graceful fallback responses when LLM is globally disabled - Create provider testing and validation system for reliable connections
124 lines
4.5 KiB
Python
124 lines
4.5 KiB
Python
"""
|
|
Google Gemini Provider for LLM requests
|
|
"""
|
|
|
|
import httpx
|
|
import json
|
|
from typing import Dict, Any, List
|
|
from .base import BaseLLMProvider, LLMRequest, LLMResponse
|
|
|
|
|
|
class GeminiProvider(BaseLLMProvider):
|
|
"""Google Gemini API provider"""
|
|
|
|
def __init__(self, config: Dict[str, Any]):
|
|
super().__init__(config)
|
|
self.api_key = config.get('api_key')
|
|
self.base_url = config.get('base_url', 'https://generativelanguage.googleapis.com/v1beta')
|
|
self.model = config.get('model', 'gemini-1.5-flash')
|
|
self.timeout = config.get('timeout', 300)
|
|
|
|
@property
|
|
def requires_api_key(self) -> bool:
|
|
return True
|
|
|
|
def get_supported_models(self) -> List[str]:
|
|
return [
|
|
'gemini-1.5-flash',
|
|
'gemini-1.5-pro',
|
|
'gemini-1.0-pro'
|
|
]
|
|
|
|
async def generate_response(self, request: LLMRequest) -> LLMResponse:
|
|
"""Generate response using Gemini API"""
|
|
try:
|
|
# Gemini uses a different API format
|
|
payload = {
|
|
'contents': [
|
|
{
|
|
'parts': [
|
|
{
|
|
'text': request.prompt
|
|
}
|
|
]
|
|
}
|
|
],
|
|
'generationConfig': {
|
|
'temperature': request.temperature or self.config.get('temperature', 0.8),
|
|
'maxOutputTokens': request.max_tokens or self.config.get('max_tokens', 2000),
|
|
'candidateCount': 1
|
|
}
|
|
}
|
|
|
|
url = f"{self.base_url}/models/{self.model}:generateContent"
|
|
params = {'key': self.api_key}
|
|
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.post(
|
|
url,
|
|
params=params,
|
|
json=payload,
|
|
timeout=self.timeout
|
|
)
|
|
|
|
if response.status_code == 200:
|
|
data = response.json()
|
|
|
|
# Extract content from Gemini response format
|
|
if 'candidates' in data and len(data['candidates']) > 0:
|
|
candidate = data['candidates'][0]
|
|
if 'content' in candidate and 'parts' in candidate['content']:
|
|
content = candidate['content']['parts'][0]['text']
|
|
|
|
# Extract token usage if available
|
|
tokens_used = None
|
|
if 'usageMetadata' in data:
|
|
tokens_used = data['usageMetadata'].get('totalTokenCount')
|
|
|
|
return LLMResponse(
|
|
content=content,
|
|
success=True,
|
|
provider='gemini',
|
|
model=self.model,
|
|
tokens_used=tokens_used
|
|
)
|
|
|
|
return LLMResponse(
|
|
content="",
|
|
success=False,
|
|
error="Gemini API returned unexpected response format",
|
|
provider='gemini'
|
|
)
|
|
else:
|
|
error_text = response.text
|
|
return LLMResponse(
|
|
content="",
|
|
success=False,
|
|
error=f"Gemini API error: {response.status_code} - {error_text}",
|
|
provider='gemini'
|
|
)
|
|
|
|
except Exception as e:
|
|
return LLMResponse(
|
|
content="",
|
|
success=False,
|
|
error=f"Gemini provider error: {str(e)}",
|
|
provider='gemini'
|
|
)
|
|
|
|
async def health_check(self) -> bool:
|
|
"""Check Gemini API health"""
|
|
try:
|
|
url = f"{self.base_url}/models"
|
|
params = {'key': self.api_key}
|
|
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.get(
|
|
url,
|
|
params=params,
|
|
timeout=10
|
|
)
|
|
return response.status_code == 200
|
|
|
|
except Exception:
|
|
return False |