Spaces:
Running
Running
File size: 16,821 Bytes
0611c31 2cb9dec b8b8738 2cb9dec 0611c31 2cb9dec 192ee60 2cb9dec 6f4f307 2cb9dec c4f488d 2cb9dec b85ea78 2cb9dec b9c19b4 2cb9dec 0fd1b97 b8b8738 2cb9dec c4f488d 2cb9dec fdc226e 2cb9dec 5c144a1 ad86a2b 5c144a1 0611c31 2cb9dec 0611c31 2cb9dec 0611c31 2cb9dec 0611c31 2cb9dec 0fd1b97 0611c31 0fd1b97 2cb9dec 2eb638f 6f4f307 2eb638f 6f4f307 0611c31 6f4f307 2eb638f 6f4f307 2eb638f 0611c31 2eb638f 2cb9dec 192ee60 2cb9dec |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 |
# import os
# from fastapi import FastAPI, Depends, HTTPException
# from fastapi.responses import JSONResponse, RedirectResponse
# from fastapi.middleware.gzip import GZipMiddleware
# from pydantic import BaseModel
# from typing import List, Dict
# from src.api.models.embedding_models import (
# CreateEmbeddingRequest,
# ReadEmbeddingRequest,
# UpdateEmbeddingRequest,
# DeleteEmbeddingRequest,
# EmbedRequest,
# )
# from src.api.database import get_db, Database, QueryExecutionError, HealthCheckError
# from src.api.services.embedding_service import EmbeddingService
# from src.api.services.huggingface_service import HuggingFaceService
# from src.api.exceptions import DatasetNotFoundError, DatasetPushError, OpenAIError
# # from src.api.dependency import get_embedding_service, get_huggingface_service
# import pandas as pd
# import logging
# from dotenv import load_dotenv
# # Load environment variables
# load_dotenv()
# # Set up structured logging
# logging.basicConfig(
# level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
# )
# logger = logging.getLogger(__name__)
# description = """A FastAPI application for similarity search with PostgreSQL and OpenAI embeddings.
# Direct/API URL:
# https://re-mind-similarity-search.hf.space
# """
# # Initialize FastAPI app
# app = FastAPI(
# title="Similarity Search API",
# description=description,
# version="1.0.0",
# )
# app.add_middleware(GZipMiddleware, minimum_size=1000)
# # Dependency to get EmbeddingService
# def get_embedding_service() -> EmbeddingService:
# return EmbeddingService(openai_api_key=os.getenv("OPENAI_API_KEY"))
# # Dependency to get HuggingFaceService
# def get_huggingface_service() -> HuggingFaceService:
# return HuggingFaceService()
# # Root endpoint redirects to /docs
# @app.get("/")
# async def root():
# return RedirectResponse(url="/docs")
# # Health check endpoint
# @app.get("/health")
# async def health_check(db: Database = Depends(get_db)):
# try:
# is_healthy = await db.health_check()
# if not is_healthy:
# raise HTTPException(status_code=500, detail="Database is unhealthy")
# return {"status": "healthy"}
# except HealthCheckError as e:
# raise HTTPException(status_code=500, detail=str(e))
# # Endpoint to generate embeddings for a list of strings
# @app.post("/embed")
# async def embed(
# request: EmbedRequest,
# embedding_service: EmbeddingService = Depends(get_embedding_service),
# ):
# """
# Generate embeddings for a list of strings and return them in the response.
# """
# try:
# # Step 1: Generate embeddings
# logger.info("Generating embeddings for list of texts...")
# embeddings = await embedding_service.create_embeddings(request.texts)
# return JSONResponse(
# content={
# "message": "Embeddings generated successfully.",
# "embeddings": embeddings,
# "num_texts": len(request.texts),
# }
# )
# except OpenAIError as e:
# logger.error(f"OpenAI API error: {e}")
# raise HTTPException(status_code=500, detail=f"OpenAI API error: {e}")
# except Exception as e:
# logger.error(f"An error occurred: {e}")
# raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# # Endpoint to create embeddings from a database query
# @app.post("/create_embedding")
# async def create_embedding(
# request: CreateEmbeddingRequest,
# db: Database = Depends(get_db),
# embedding_service: EmbeddingService = Depends(get_embedding_service),
# huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
# ):
# """
# Create embeddings for the target column in the dataset.
# """
# try:
# # Step 1: Query the database
# logger.info("Fetching data from the database...")
# result = await db.fetch(request.query)
# df = pd.DataFrame(result)
# # Step 2: Generate embeddings
# df = await embedding_service.create_embeddings(
# df, request.target_column, request.output_column
# )
# # Step 3: Push to Hugging Face Hub
# await huggingface_service.push_to_hub(df, request.dataset_name)
# return JSONResponse(
# content={
# "message": "Embeddings created and pushed to Hugging Face Hub.",
# "dataset_name": request.dataset_name,
# "num_rows": len(df),
# }
# )
# except QueryExecutionError as e:
# logger.error(f"Database query failed: {e}")
# raise HTTPException(status_code=500, detail=f"Database query failed: {e}")
# except OpenAIError as e:
# logger.error(f"OpenAI API error: {e}")
# raise HTTPException(status_code=500, detail=f"OpenAI API error: {e}")
# except DatasetPushError as e:
# logger.error(f"Failed to push dataset: {e}")
# raise HTTPException(status_code=500, detail=f"Failed to push dataset: {e}")
# except Exception as e:
# logger.error(f"An error occurred: {e}")
# raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# # Endpoint to read embeddings
# @app.post("/read_embeddings")
# async def read_embeddings(
# request: ReadEmbeddingRequest,
# huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
# ):
# """
# Read embeddings from a Hugging Face dataset.
# """
# try:
# df = await huggingface_service.read_dataset(request.dataset_name)
# return df
# except DatasetNotFoundError as e:
# logger.error(f"Dataset not found: {e}")
# raise HTTPException(status_code=404, detail=f"Dataset not found: {e}")
# except Exception as e:
# logger.error(f"An error occurred: {e}")
# raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# # Endpoint to update embeddings
# # @app.post("/update_embeddings")
# # async def update_embeddings(
# # request: UpdateEmbeddingRequest,
# # huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
# # ):
# # """
# # Update embeddings in a Hugging Face dataset.
# # """
# # try:
# # df = await huggingface_service.update_dataset(
# # request.dataset_name, request.updates
# # )
# # return {
# # "message": "Embeddings updated successfully.",
# # "dataset_name": request.dataset_name,
# # }
# # except DatasetPushError as e:
# # logger.error(f"Failed to update dataset: {e}")
# # raise HTTPException(status_code=500, detail=f"Failed to update dataset: {e}")
# # except Exception as e:
# # logger.error(f"An error occurred: {e}")
# # raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# @app.post("/update_embeddings")
# async def update_embeddings(
# request: UpdateEmbeddingRequest,
# huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
# ):
# """
# Update embeddings in a Hugging Face dataset by generating embeddings for new data and concatenating it with the existing dataset.
# """
# try:
# # Call the update_dataset method to generate embeddings, concatenate, and push the updated dataset
# updated_df = await huggingface_service.update_dataset(
# request.dataset_name,
# request.updates,
# request.target_column,
# request.output_column,
# )
# return {
# "message": "Embeddings updated successfully.",
# "dataset_name": request.dataset_name,
# "num_rows": len(updated_df),
# }
# except DatasetPushError as e:
# logger.error(f"Failed to update dataset: {e}")
# raise HTTPException(status_code=500, detail=f"Failed to update dataset: {e}")
# except Exception as e:
# logger.error(f"An error occurred: {e}")
# raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# # Endpoint to delete embeddings
# @app.post("/delete_embeddings")
# async def delete_embeddings(
# request: DeleteEmbeddingRequest,
# huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
# ):
# """
# Delete embeddings from a Hugging Face dataset.
# """
# try:
# await huggingface_service.delete_dataset(request.dataset_name)
# return {
# "message": "Embeddings deleted successfully.",
# "dataset_name": request.dataset_name,
# }
# except DatasetPushError as e:
# logger.error(f"Failed to delete columns: {e}")
# raise HTTPException(status_code=500, detail=f"Failed to delete columns: {e}")
# except Exception as e:
# logger.error(f"An error occurred: {e}")
# raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
import os
from fastapi import FastAPI, Depends, HTTPException
from fastapi.responses import JSONResponse, RedirectResponse
from fastapi.middleware.gzip import GZipMiddleware
from pydantic import BaseModel
from typing import List, Dict
from datasets import Dataset
from src.api.models.embedding_models import (
CreateEmbeddingRequest,
ReadEmbeddingRequest,
UpdateEmbeddingRequest,
DeleteEmbeddingRequest,
EmbedRequest,
)
from src.api.database import get_db, Database, QueryExecutionError, HealthCheckError
from src.api.services.embedding_service import EmbeddingService
from src.api.services.huggingface_service import HuggingFaceService
from src.api.exceptions import DatasetNotFoundError, DatasetPushError, OpenAIError
import logging
from dotenv import load_dotenv
# Load environment variables
load_dotenv()
# Set up structured logging
logging.basicConfig(
level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
logger = logging.getLogger(__name__)
description = """A FastAPI application for similarity search with PostgreSQL and OpenAI embeddings.
Direct/API URL:
https://re-mind-similarity-search.hf.space
"""
# Initialize FastAPI app
app = FastAPI(
title="Similarity Search API",
description=description,
version="1.0.0",
)
app.add_middleware(GZipMiddleware, minimum_size=1000)
# Dependency to get EmbeddingService
def get_embedding_service() -> EmbeddingService:
return EmbeddingService(openai_api_key=os.getenv("OPENAI_API_KEY"))
# Dependency to get HuggingFaceService
def get_huggingface_service() -> HuggingFaceService:
return HuggingFaceService()
# Root endpoint redirects to /docs
@app.get("/")
async def root():
return RedirectResponse(url="/docs")
# Health check endpoint
@app.get("/health")
async def health_check(db: Database = Depends(get_db)):
try:
is_healthy = await db.health_check()
if not is_healthy:
raise HTTPException(status_code=500, detail="Database is unhealthy")
return {"status": "healthy"}
except HealthCheckError as e:
raise HTTPException(status_code=500, detail=str(e))
# Endpoint to generate embeddings for a list of strings
@app.post("/embed")
async def embed(
request: EmbedRequest,
embedding_service: EmbeddingService = Depends(get_embedding_service),
):
"""
Generate embeddings for a list of strings and return them in the response.
"""
try:
# Step 1: Generate embeddings
logger.info("Generating embeddings for list of texts...")
embeddings = await embedding_service.create_embeddings(request.texts)
return JSONResponse(
content={
"message": "Embeddings generated successfully.",
"embeddings": embeddings,
"num_texts": len(request.texts),
}
)
except OpenAIError as e:
logger.error(f"OpenAI API error: {e}")
raise HTTPException(status_code=500, detail=f"OpenAI API error: {e}")
except Exception as e:
logger.error(f"An error occurred: {e}")
raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# Endpoint to create embeddings from a database query
@app.post("/create_embedding")
async def create_embedding(
request: CreateEmbeddingRequest,
db: Database = Depends(get_db),
embedding_service: EmbeddingService = Depends(get_embedding_service),
huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
):
"""
Create embeddings for the target column in the dataset.
"""
try:
# Step 1: Query the database
logger.info("Fetching data from the database...")
result = await db.fetch(request.query)
# logger.info(f"{result}")
dataset = Dataset.from_dict(result)
# Step 2: Generate embeddings
dataset = await embedding_service.create_embeddings(
dataset, request.target_column, request.output_column
)
# Step 3: Push to Hugging Face Hub
await huggingface_service.push_to_hub(dataset, request.dataset_name)
return JSONResponse(
content={
"message": "Embeddings created and pushed to Hugging Face Hub.",
"dataset_name": request.dataset_name,
"num_rows": len(dataset),
}
)
except QueryExecutionError as e:
logger.error(f"Database query failed: {e}")
raise HTTPException(status_code=500, detail=f"Database query failed: {e}")
except OpenAIError as e:
logger.error(f"OpenAI API error: {e}")
raise HTTPException(status_code=500, detail=f"OpenAI API error: {e}")
except DatasetPushError as e:
logger.error(f"Failed to push dataset: {e}")
raise HTTPException(status_code=500, detail=f"Failed to push dataset: {e}")
except Exception as e:
logger.error(f"An error occurred: {e}")
raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# Endpoint to read embeddings
@app.post("/read_embeddings")
async def read_embeddings(
request: ReadEmbeddingRequest,
huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
):
"""
Read embeddings from a Hugging Face dataset.
"""
try:
dataset = await huggingface_service.read_dataset(request.dataset_name)
return dataset.to_dict()
except DatasetNotFoundError as e:
logger.error(f"Dataset not found: {e}")
raise HTTPException(status_code=404, detail=f"Dataset not found: {e}")
except Exception as e:
logger.error(f"An error occurred: {e}")
raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# Endpoint to update embeddings
@app.post("/update_embeddings")
async def update_embeddings(
request: UpdateEmbeddingRequest,
huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
):
"""
Update embeddings in a Hugging Face dataset by generating embeddings for new data and concatenating it with the existing dataset.
"""
try:
# Call the update_dataset method to generate embeddings, concatenate, and push the updated dataset
updated_dataset = await huggingface_service.update_dataset(
request.dataset_name,
request.updates,
request.target_column,
request.output_column,
)
return {
"message": "Embeddings updated successfully.",
"dataset_name": request.dataset_name,
"num_rows": len(updated_dataset),
}
except DatasetPushError as e:
logger.error(f"Failed to update dataset: {e}")
raise HTTPException(status_code=500, detail=f"Failed to update dataset: {e}")
except Exception as e:
logger.error(f"An error occurred: {e}")
raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
# Endpoint to delete embeddings
@app.post("/delete_embeddings")
async def delete_embeddings(
request: DeleteEmbeddingRequest,
huggingface_service: HuggingFaceService = Depends(get_huggingface_service),
):
"""
Delete embeddings from a Hugging Face dataset.
"""
try:
await huggingface_service.delete_dataset(request.dataset_name)
return {
"message": "Embeddings deleted successfully.",
"dataset_name": request.dataset_name,
}
except DatasetPushError as e:
logger.error(f"Failed to delete columns: {e}")
raise HTTPException(status_code=500, detail=f"Failed to delete columns: {e}")
except Exception as e:
logger.error(f"An error occurred: {e}")
raise HTTPException(status_code=500, detail=f"An error occurred: {e}")
|