matt/discord-fishbowl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix Docker startup script and complete application deployment

Browse Source 
- Update docker-start.sh to force correct profiles (qdrant, admin)
- Fix PostgreSQL port mapping from 5432 to 15432 across all configs
- Resolve MCP import conflicts by renaming src/mcp to src/mcp_servers
- Fix admin interface StaticFiles mount syntax error
- Update LLM client to support both Ollama and OpenAI-compatible APIs
- Configure host networking for Discord bot container access
- Correct database connection handling for async context managers
- Update environment variables and Docker compose configurations
- Add missing production dependencies and Dockerfile improvements
This commit is contained in:
root
2025-07-05 15:09:29 -07:00
parent 824b118e93
commit 3d9e8ffbf0
59 changed files with 1100 additions and 244 deletions
Download Patch File Download Diff File Expand all files Collapse all files

99
src/llm/client.py
View File

@@ -4,8 +4,8 @@ import json
import time
from typing import Dict, Any, Optional, List
from datetime import datetime, timedelta
from ..utils.config import get_settings
from ..utils.logging import log_llm_interaction, log_error_with_context, log_system_health
from utils.config import get_settings
from utils.logging import log_llm_interaction, log_error_with_context, log_system_health
import logging
logger = logging.getLogger(__name__)
@@ -55,33 +55,61 @@ class LLMClient:
start_time = time.time()
# Prepare request
request_data = {
"model": self.model,
"prompt": prompt,
"options": {
"temperature": temperature or self.temperature,
"num_predict": max_tokens or self.max_tokens,
"top_p": 0.9,
"top_k": 40,
"repeat_penalty": 1.1
},
"stream": False
}
# Make API call
# Try OpenAI-compatible API first (KoboldCPP, etc.)
async with httpx.AsyncClient(timeout=self.timeout) as client:
response = await client.post(
f"{self.base_url}/api/generate",
json=request_data,
headers={"Content-Type": "application/json"}
)
try:
# OpenAI-compatible request
request_data = {
"model": self.model,
"messages": [{"role": "user", "content": prompt}],
"temperature": temperature or self.temperature,
"max_tokens": max_tokens or self.max_tokens,
"top_p": 0.9,
"stream": False
}
response = await client.post(
f"{self.base_url}/chat/completions",
json=request_data,
headers={"Content-Type": "application/json"}
)
response.raise_for_status()
result = response.json()
if 'choices' in result and result['choices'] and 'message' in result['choices'][0]:
generated_text = result['choices'][0]['message']['content'].strip()
else:
generated_text = None
except (httpx.HTTPStatusError, httpx.RequestError, KeyError):
# Fallback to Ollama API
request_data = {
"model": self.model,
"prompt": prompt,
"options": {
"temperature": temperature or self.temperature,
"num_predict": max_tokens or self.max_tokens,
"top_p": 0.9,
"top_k": 40,
"repeat_penalty": 1.1
},
"stream": False
}
response = await client.post(
f"{self.base_url}/api/generate",
json=request_data,
headers={"Content-Type": "application/json"}
)
response.raise_for_status()
result = response.json()
if 'response' in result and result['response']:
generated_text = result['response'].strip()
else:
generated_text = None
response.raise_for_status()
result = response.json()
if 'response' in result and result['response']:
generated_text = result['response'].strip()
if generated_text:
# Cache the response
self._cache_response(cache_key, generated_text)
@@ -143,11 +171,18 @@ class LLMClient:
"""Check if the LLM model is available"""
try:
async with httpx.AsyncClient(timeout=10) as client:
response = await client.get(f"{self.base_url}/api/tags")
response.raise_for_status()
models = response.json()
available_models = [model.get('name', '') for model in models.get('models', [])]
# Try OpenAI-compatible API first (KoboldCPP, etc.)
try:
response = await client.get(f"{self.base_url}/models")
response.raise_for_status()
models = response.json()
available_models = [model.get('id', '') for model in models.get('data', [])]
except (httpx.HTTPStatusError, httpx.RequestError):
# Fallback to Ollama API
response = await client.get(f"{self.base_url}/api/tags")
response.raise_for_status()
models = response.json()
available_models = [model.get('name', '') for model in models.get('models', [])]
is_available = any(self.model in model_name for model_name in available_models)