Upload folder using huggingface_hub

.idea/workspace.xml

@@ -267,7 +267,7 @@
       <workItem from="1747779058058" duration="9506000" />
       <workItem from="1747841281902" duration="245000" />
       <workItem from="1749511880222" duration="3463000" />
-      <workItem from="1749582965687" duration="10202000" />
+      <workItem from="1749582965687" duration="12333000" />
     </task>
     <task id="LOCAL-00001" summary="Last commit before refacto">
       <option name="closed" value="true" />

app.py

@@ -6,13 +6,11 @@ from src.aiagent.utils.ecom_tools import (search_on_amazon,
 from src.aiagent.ui.main_gradio import GradioUI
 import yaml
 from src.aiagent.core.custom_python_executor import LocalPythonExecutor
-import requests
 
-# Machine localisation for debugging
-ip = requests.get("https://api.ipify.org").text
-location = requests.get(f"https://ipinfo.io/{ip}/json").json()
-print("IP:", ip)
-print("Localisation:", location)
+# with open('config/secrets.yaml') as f:
+#     SECRETS = yaml.safe_load(f)
+#
+# os.environ['GEMINI_API_KEY'] = SECRETS['gemini_token']
 
 tools_model = LiteLLMModel(model_id='gemini/gemini-2.0-flash')
 # reasoning_model = LiteLLMModel(model_id='gpt-4o-mini')

src/aiagent/utils/ecom_tools.py

@@ -5,7 +5,6 @@ import json
 import pandas as pd
 import re
 from typing import Any, Optional
-import random
 
 
 class ParserProductDescriptionWithGuideTool(Tool):
@@ -90,13 +89,11 @@ class GetProductDescriptionTool(Tool):
     def __init__(self):
         super().__init__()
         self.headers = {
-            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 13_3_1) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.0 Safari/605.1.15',
-            'Accept-Language': 'en-US;q=0.9,en;q=0.8',
-            'Accept-Encoding': 'gzip, deflate, br',
-            'Connection': 'keep-alive',
-            'Upgrade-Insecure-Requests': '1',
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36",
+            "Accept-Language": "en-US,en;q=0.9"
         }
 
+
     @staticmethod
     def _clean_product_url(product_url: str) -> str:
         pattern = r"(https://www\.amazon\.[a-z.]+/[^/]+/dp/[^/]+)"
@@ -172,26 +169,19 @@ def search_on_amazon(keyword: str) -> list[dict]:
     """
 
     headers = {
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36',
-        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
-        'Accept-Language': 'en-US,en;q=0.9',
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
+        'Accept-Language': 'fr-FR,fr;q=0.9,en-US;q=0.8,en;q=0.7',
         'Accept-Encoding': 'gzip, deflate, br',
         'Connection': 'keep-alive',
         'Upgrade-Insecure-Requests': '1',
-        'Sec-Fetch-Dest': 'document',
-        'Sec-Fetch-Mode': 'navigate',
-        'Sec-Fetch-Site': 'none',
-        'Sec-Fetch-User': '?1',
     }
 
-    url = f"https://www.amazon.com/s?k={keyword.replace(' ', '+')}"  # Could be adapted for other countries
-
-    print('debugging url', url)
+    url = f"https://www.amazon.fr/s?k={keyword.replace(' ', '+')}"  # Could be adapted for other countries
 
     response = requests.get(url, headers=headers)
 
     if response.status_code != 200:
-        print("Error during page loading")
+        print("Error during page loading", response.status_code)
 
     # Parsing using beautifulSoup
     soup = BeautifulSoup(response.text, 'html.parser')
@@ -220,7 +210,7 @@ def search_on_amazon(keyword: str) -> list[dict]:
             product_json['image_url'] = image_element.get('src')
 
         if link_element:
-            product_json['product_link'] = 'https://www.amazon.com' + link_element['href']
+            product_json['product_link'] = 'https://www.amazon.fr' + link_element['href']
 
         if price_element:
             product_json['price'] = price_element.get_text().replace("\\xa0", " ").replace("\xa0", " ")
@@ -305,7 +295,7 @@ class FilterProduct(Tool):
                 "Tu dois répondre uniquement par 'oui' ou 'non' (sans autre explication), selon que le produit satisfait la condition ou non en t'aidant des differents champs du dictionnaire."
                 "La réponse doit être exactement 'oui' ou 'non', en minuscules."
             )},
-            {"role": "user", "content": f"Product : {product}\n Condition : {condition}"}
+            {"role": "user", "content": f"Produit : {product}\n Condition : {condition}"}
         ]
 
         result = self.model(messages).content.strip().lower()