Spaces:
Running
Running
File size: 3,601 Bytes
79b95cf |
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 |
import os
import whisper
import requests
from flask import Flask, request, jsonify, render_template
from dotenv import load_dotenv
from deepgram import DeepgramClient, PrerecordedOptions
import tempfile
import json
import subprocess
from youtube_transcript_api import YouTubeTranscriptApi
import warnings
warnings.filterwarnings("ignore", message="FP16 is not supported on CPU; using FP32 instead")
app = Flask(__name__)
print("APP IS RUNNING, ANIKET")
# Load the .env file
load_dotenv()
print("ENV LOADED, ANIKET")
# Fetch the API key from the .env file
API_KEY = os.getenv("FIRST_API_KEY")
DEEPGRAM_API_KEY = os.getenv("SECOND_API_KEY")
# Ensure the API key is loaded correctly
if not API_KEY:
raise ValueError("API Key not found. Make sure it is set in the .env file.")
if not DEEPGRAM_API_KEY:
raise ValueError("DEEPGRAM_API_KEY not found. Make sure it is set in the .env file.")
GEMINI_API_ENDPOINT = "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-latest:generateContent"
GEMINI_API_KEY = API_KEY
@app.route("/", methods=["GET"])
def health_check():
return jsonify({"status": "success", "message": "API is running successfully!"}), 200
def query_gemini_api(transcription):
"""
Send transcription text to Gemini API and fetch structured recipe information synchronously.
"""
try:
# Define the structured prompt
prompt = (
"Analyze the provided cooking video transcription and extract the following structured information:\n"
"1. Recipe Name: Identify the name of the dish being prepared.\n"
"2. Ingredients List: Extract a detailed list of ingredients with their respective quantities (if mentioned).\n"
"3. Steps for Preparation: Provide a step-by-step breakdown of the recipe's preparation process, organized and numbered sequentially.\n"
"4. Cooking Techniques Used: Highlight the cooking techniques demonstrated in the video, such as searing, blitzing, wrapping, etc.\n"
"5. Equipment Needed: List all tools, appliances, or utensils mentioned, e.g., blender, hot pan, cling film, etc.\n"
"6. Nutritional Information (if inferred): Provide an approximate calorie count or nutritional breakdown based on the ingredients used.\n"
"7. Serving size: In count of people or portion size.\n"
"8. Special Notes or Variations: Include any specific tips, variations, or alternatives mentioned.\n"
"9. Festive or Thematic Relevance: Note if the recipe has any special relevance to holidays, events, or seasons.\n"
f"Text: {transcription}\n"
)
# Prepare the payload and headers
payload = {
"contents": [
{
"parts": [
{"text": prompt}
]
}
]
}
headers = {"Content-Type": "application/json"}
# Send request to Gemini API synchronously
response = requests.post(
f"{GEMINI_API_ENDPOINT}?key={GEMINI_API_KEY}",
json=payload,
headers=headers,
)
# Raise error if response code is not 200
response.raise_for_status()
data = response.json()
return data.get("candidates", [{}])[0].get("content", {}).get("parts", [{}])[0].get("text", "No result found")
except requests.exceptions.RequestException as e:
print(f"Error querying Gemini API: {e}")
return {"error": str(e)}
if __name__ == '__main__':
app.run(debug=True)
|