Spaces:
Running
Running
File size: 5,304 Bytes
bc82930 2cb9dec bc82930 2cb9dec bc82930 e0b1978 2cb9dec bc82930 e0b1978 bc82930 2cb9dec e0b1978 2cb9dec e0b1978 |
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 |
# from openai import AsyncOpenAI
# import logging
# from typing import List, Dict
# import pandas as pd
# import asyncio
# from src.api.exceptions import OpenAIError
# # Set up structured logging
# logging.basicConfig(
# level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
# )
# logger = logging.getLogger(__name__)
# class EmbeddingService:
# def __init__(
# self,
# openai_api_key: str,
# model: str = "text-embedding-3-small",
# batch_size: int = 100,
# ):
# self.client = AsyncOpenAI(api_key=openai_api_key)
# self.model = model
# self.batch_size = batch_size
# async def get_embedding(self, text: str) -> List[float]:
# """Generate embeddings for the given text using OpenAI."""
# text = text.replace("\n", " ")
# try:
# response = await self.client.embeddings.create(
# input=[text], model=self.model
# )
# return response.data[0].embedding
# except Exception as e:
# logger.error(f"Failed to generate embedding: {e}")
# raise OpenAIError(f"OpenAI API error: {e}")
# async def create_embeddings(
# self, df: pd.DataFrame, target_column: str, output_column: str
# ) -> pd.DataFrame:
# """Create embeddings for the target column in the dataset."""
# logger.info("Generating embeddings...")
# batches = [
# df[i : i + self.batch_size] for i in range(0, len(df), self.batch_size)
# ]
# processed_batches = await asyncio.gather(
# *[
# self._process_batch(batch, target_column, output_column)
# for batch in batches
# ]
# )
# return pd.concat(processed_batches)
# async def _process_batch(
# self, df_batch: pd.DataFrame, target_column: str, output_column: str
# ) -> pd.DataFrame:
# """Process a batch of rows to generate embeddings."""
# embeddings = await asyncio.gather(
# *[self.get_embedding(row[target_column]) for _, row in df_batch.iterrows()]
# )
# df_batch[output_column] = embeddings
# return df_batch
from openai import AsyncOpenAI
import logging
from typing import List, Dict
import pandas as pd
import asyncio
from src.api.exceptions import OpenAIError
# Set up structured logging
logging.basicConfig(
level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
logger = logging.getLogger(__name__)
class EmbeddingService:
def __init__(
self,
openai_api_key: str,
model: str = "text-embedding-3-small",
batch_size: int = 10,
max_concurrent_requests: int = 10, # Limit to 10 concurrent requests
):
self.client = AsyncOpenAI(api_key=openai_api_key)
self.model = model
self.batch_size = batch_size
self.semaphore = asyncio.Semaphore(max_concurrent_requests) # Rate limiter
self.total_requests = 0 # Total number of requests to process
self.completed_requests = 0 # Number of completed requests
async def get_embedding(self, text: str) -> List[float]:
"""Generate embeddings for the given text using OpenAI."""
text = text.replace("\n", " ")
try:
async with self.semaphore: # Acquire a semaphore slot
response = await self.client.embeddings.create(
input=[text], model=self.model
)
self.completed_requests += 1 # Increment completed requests
self._log_progress() # Log progress
return response.data[0].embedding
except Exception as e:
logger.error(f"Failed to generate embedding: {e}")
raise OpenAIError(f"OpenAI API error: {e}")
async def create_embeddings(
self, df: pd.DataFrame, target_column: str, output_column: str
) -> pd.DataFrame:
"""Create embeddings for the target column in the dataset."""
logger.info("Generating embeddings...")
self.total_requests = len(df) # Set total number of requests
self.completed_requests = 0 # Reset completed requests counter
batches = [
df[i : i + self.batch_size] for i in range(0, len(df), self.batch_size)
]
processed_batches = await asyncio.gather(
*[
self._process_batch(batch, target_column, output_column)
for batch in batches
]
)
return pd.concat(processed_batches)
async def _process_batch(
self, df_batch: pd.DataFrame, target_column: str, output_column: str
) -> pd.DataFrame:
"""Process a batch of rows to generate embeddings."""
embeddings = await asyncio.gather(
*[self.get_embedding(row[target_column]) for _, row in df_batch.iterrows()]
)
df_batch[output_column] = embeddings
return df_batch
def _log_progress(self):
"""Log the progress of embedding generation."""
progress = (self.completed_requests / self.total_requests) * 100
logger.info(
f"Progress: {self.completed_requests}/{self.total_requests} ({progress:.2f}%)"
)
|