File size: 11,409 Bytes
aa61236 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 |
"""API client for HuggingFace Inference API and OpenAI."""
import httpx
import asyncio
from typing import List, Dict, Any, Optional
from .config_free import (
OPENAI_API_KEY,
HUGGINGFACE_API_KEY,
DEFAULT_TIMEOUT,
MAX_RETRIES,
RETRY_DELAY
)
async def query_openai_model(
model: str,
messages: List[Dict[str, str]],
timeout: float = DEFAULT_TIMEOUT,
max_retries: int = MAX_RETRIES
) -> Optional[Dict[str, Any]]:
"""
Query an OpenAI model.
Args:
model: OpenAI model name (e.g., "gpt-4o-mini")
messages: List of message dicts with 'role' and 'content'
timeout: Request timeout in seconds
max_retries: Maximum retry attempts
Returns:
Response dict with 'content', or None if failed
"""
headers = {
"Authorization": f"Bearer {OPENAI_API_KEY}",
"Content-Type": "application/json",
}
payload = {
"model": model,
"messages": messages,
"temperature": 0.7,
}
for attempt in range(max_retries + 1):
try:
async with httpx.AsyncClient(timeout=timeout) as client:
response = await client.post(
"https://api.openai.com/v1/chat/completions",
headers=headers,
json=payload
)
response.raise_for_status()
data = response.json()
content = data["choices"][0]["message"]["content"]
return {"content": content}
except httpx.TimeoutException as e:
print(f"⏱️ Timeout querying OpenAI {model} (attempt {attempt + 1}/{max_retries + 1})")
if attempt < max_retries:
await asyncio.sleep(RETRY_DELAY * (attempt + 1))
continue
return None
except httpx.HTTPStatusError as e:
print(f"🚫 HTTP error querying OpenAI {model}: {e.response.status_code}")
if 400 <= e.response.status_code < 500:
return None
if attempt < max_retries:
await asyncio.sleep(RETRY_DELAY * (attempt + 1))
continue
return None
except Exception as e:
print(f"❌ Error querying OpenAI {model}: {e}")
if attempt < max_retries:
await asyncio.sleep(RETRY_DELAY)
continue
return None
return None
async def query_huggingface_model(
model: str,
messages: List[Dict[str, str]],
timeout: float = DEFAULT_TIMEOUT,
max_retries: int = MAX_RETRIES
) -> Optional[Dict[str, Any]]:
"""
Query a HuggingFace model via Inference API (FREE).
Args:
model: HuggingFace model ID (e.g., "meta-llama/Llama-3.3-70B-Instruct")
messages: List of message dicts with 'role' and 'content'
timeout: Request timeout in seconds
max_retries: Maximum retry attempts
Returns:
Response dict with 'content', or None if failed
"""
headers = {
"Authorization": f"Bearer {HUGGINGFACE_API_KEY}",
"Content-Type": "application/json",
}
# Convert messages to prompt format for HuggingFace
prompt = format_messages_for_hf(messages)
payload = {
"inputs": prompt,
"parameters": {
"max_new_tokens": 2048,
"temperature": 0.7,
"top_p": 0.9,
"do_sample": True,
}
}
api_url = f"https://api-inference.huggingface.co/models/{model}"
for attempt in range(max_retries + 1):
try:
async with httpx.AsyncClient(timeout=timeout) as client:
response = await client.post(api_url, headers=headers, json=payload)
response.raise_for_status()
data = response.json()
# Handle different response formats
if isinstance(data, list) and len(data) > 0:
content = data[0].get("generated_text", "")
# Remove the prompt from the response
if content.startswith(prompt):
content = content[len(prompt):].strip()
elif isinstance(data, dict):
content = data.get("generated_text", "")
if content.startswith(prompt):
content = content[len(prompt):].strip()
else:
content = str(data)
return {"content": content}
except httpx.TimeoutException as e:
print(f"⏱️ Timeout querying HF {model} (attempt {attempt + 1}/{max_retries + 1})")
if attempt < max_retries:
await asyncio.sleep(RETRY_DELAY * (attempt + 1))
continue
return None
except httpx.HTTPStatusError as e:
error_msg = e.response.text
print(f"🚫 HTTP {e.response.status_code} querying HF {model}: {error_msg[:100]}")
# Model is loading - retry with longer delay
if "loading" in error_msg.lower():
print(f"⏳ Model is loading, waiting 20s...")
await asyncio.sleep(20)
if attempt < max_retries:
continue
# Don't retry on client errors (except loading)
if 400 <= e.response.status_code < 500:
return None
if attempt < max_retries:
await asyncio.sleep(RETRY_DELAY * (attempt + 1))
continue
return None
except Exception as e:
print(f"❌ Error querying HF {model}: {e}")
if attempt < max_retries:
await asyncio.sleep(RETRY_DELAY)
continue
return None
return None
def format_messages_for_hf(messages: List[Dict[str, str]]) -> str:
"""
Format chat messages for HuggingFace models.
Args:
messages: List of message dicts with 'role' and 'content'
Returns:
Formatted prompt string
"""
# Use common chat template format
prompt = ""
for msg in messages:
role = msg["role"]
content = msg["content"]
if role == "system":
prompt += f"<|system|>\n{content}\n"
elif role == "user":
prompt += f"<|user|>\n{content}\n"
elif role == "assistant":
prompt += f"<|assistant|>\n{content}\n"
# Add assistant prefix for response
prompt += "<|assistant|>\n"
return prompt
async def query_model(
model_config: Dict[str, str],
messages: List[Dict[str, str]],
timeout: float = DEFAULT_TIMEOUT
) -> Optional[Dict[str, Any]]:
"""
Query a model based on its configuration (provider-agnostic).
Args:
model_config: Dict with 'provider' and 'model' keys
messages: List of message dicts
timeout: Request timeout
Returns:
Response dict or None
"""
provider = model_config["provider"]
model = model_config["model"]
if provider == "openai":
return await query_openai_model(model, messages, timeout)
elif provider == "huggingface":
return await query_huggingface_model(model, messages, timeout)
else:
print(f"❌ Unknown provider: {provider}")
return None
async def query_model_stream(
model_config: Dict[str, str],
messages: List[Dict[str, str]],
timeout: float = DEFAULT_TIMEOUT
):
"""
Query a model and stream the response.
Args:
model_config: Dict with 'provider' and 'model' keys
messages: List of message dicts
timeout: Request timeout
Yields:
Content chunks
"""
provider = model_config["provider"]
model = model_config["model"]
if provider == "openai":
async for chunk in stream_openai_model(model, messages, timeout):
yield chunk
elif provider == "huggingface":
# HF Inference API doesn't support streaming well, fallback to full response
response = await query_huggingface_model(model, messages, timeout)
if response:
yield response["content"]
else:
yield "[Error: Failed to get response]"
else:
yield f"[Error: Unknown provider {provider}]"
async def stream_openai_model(
model: str,
messages: List[Dict[str, str]],
timeout: float = DEFAULT_TIMEOUT
):
"""Stream OpenAI model response."""
headers = {
"Authorization": f"Bearer {OPENAI_API_KEY}",
"Content-Type": "application/json",
}
payload = {
"model": model,
"messages": messages,
"temperature": 0.7,
"stream": True,
}
import json
try:
async with httpx.AsyncClient(timeout=timeout) as client:
async with client.stream(
"POST",
"https://api.openai.com/v1/chat/completions",
headers=headers,
json=payload
) as response:
response.raise_for_status()
async for line in response.aiter_lines():
if line.startswith("data: "):
data_str = line[6:]
if data_str.strip() == "[DONE]":
break
try:
data = json.loads(data_str)
delta = data["choices"][0]["delta"]
content = delta.get("content")
if content:
yield content
except (json.JSONDecodeError, KeyError):
pass
except Exception as e:
print(f"❌ Error streaming OpenAI {model}: {e}")
yield f"\n[Error: {str(e)}]"
async def query_models_parallel(
model_configs: List[Dict[str, str]],
messages: List[Dict[str, str]],
timeout: float = DEFAULT_TIMEOUT
) -> Dict[str, Optional[Dict[str, Any]]]:
"""
Query multiple models in parallel.
Args:
model_configs: List of model config dicts
messages: Messages to send to each model
timeout: Request timeout
Returns:
Dict mapping model ID to response
"""
print(f"🚀 Querying {len(model_configs)} models in parallel...")
tasks = [query_model(config, messages, timeout) for config in model_configs]
responses = await asyncio.gather(*tasks, return_exceptions=True)
result = {}
for config, response in zip(model_configs, responses):
model_id = config["id"]
if isinstance(response, Exception):
print(f"❌ Model {model_id} raised exception: {response}")
result[model_id] = None
else:
result[model_id] = response
status = "✅" if response else "❌"
print(f"{status} Model {model_id} completed")
successful = sum(1 for r in result.values() if r is not None)
print(f"📊 {successful}/{len(model_configs)} models responded successfully")
return result
|