Update main.py

main.py

@@ -8,8 +8,7 @@ import uuid
 import langsmith as ls
 from pathlib import Path
 import chainlit as cl
-#from mistralai.client import MistralClient
-#from mistralai import Mistral, UserMessage, SystemMessage
+
 from deep_translator import GoogleTranslator
 from operator import itemgetter
 from langchain_huggingface import HuggingFaceEndpoint
@@ -17,10 +16,12 @@ from langchain.schema.runnable import Runnable, RunnablePassthrough, RunnableLam
 from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain.memory import ChatMessageHistory, ConversationBufferMemory
 from langchain.schema.runnable.config import RunnableConfig
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_pinecone import PineconeVectorStore
 
 from offres_emploi import Api
 from offres_emploi.utils import dt_to_str_iso
-#os.environ["GITHUB_TOKEN"] = os.environ["GITHUB_TOKEN"]
+
 os.environ['HUGGINGFACEHUB_API_TOKEN'] = os.environ['HUGGINGFACEHUB_API_TOKEN']
 
 session_id = str(uuid.uuid4())
@@ -81,6 +82,13 @@ def connexion_France_Travail():
                 client_secret=os.getenv('POLE_EMPLOI_CLIENT_SECRET'))
     return client
 
+def connexion_vector_database():
+    os.environ['PINECONE_API_KEY'] = os.environ['PINECONE_API_KEY']
+    os.environ['PINECONE_INDEX_NAME'] = os.environ['PINECONE_INDEX_NAME'] = 'all-skills'
+    embeddings = HuggingFaceEmbeddings()
+    docsearch = PineconeVectorStore.from_existing_index(os.environ['PINECONE_INDEX_NAME'], embeddings)
+    return docsearch
+
 @traceable(run_type="chain", name="API France Travail : recherche par code ROME",)
 def API_France_Travail_ROME(romeListArray):
     client = connexion_France_Travail()
@@ -109,19 +117,28 @@ def API_France_Travail_ROME(romeListArray):
 
 @traceable(run_type="chain", name="API France Travail : recherche par métier type",)
 def API_France_Travail_Metier(metier):
+    os.environ['PINECONE_API_KEYROME'] = os.environ['PINECONE_API_KEYROME']
+    docsearch = await connexion_vector_database()
+    retrieve_comp = docsearch.similarity_search(metier, k=2, filter={"categorie": {"$eq": os.environ['PINECONE_API_KEYROME']}})
+    codeRome = []
+    for i in range(0,len(retrieve_comp)):
+      codeRome.append(retrieve_comp[i].metadata['code_rome'])
+
     client = connexion_France_Travail()
     todayDate = datetime.datetime.today()
     month, year = (todayDate.month-1, todayDate.year) if todayDate.month != 1 else (12, todayDate.year-1)
     start_dt = todayDate.replace(day=1, month=month, year=year)
     end_dt = datetime.datetime.today()
     results = []  
-    params = {"motsCles": metier,'minCreationDate': dt_to_str_iso(start_dt),'maxCreationDate': dt_to_str_iso(end_dt),'range':'0-149'}
-    try:
-        search_on_big_data = client.search(params=params)
-        results += search_on_big_data["resultats"]
-    except:
-        print("Il n'y a pas d'offres d'emploi.")
-        
+    
+    for k in codeRome:
+        params = {"motsCles": k,'minCreationDate': dt_to_str_iso(start_dt),'maxCreationDate': dt_to_str_iso(end_dt),'range':'0-149'}
+        try:
+            search_on_big_data = client.search(params=params)
+            results += search_on_big_data["resultats"]
+        except:
+            print("Il n'y a pas d'offres d'emploi.")
+    
     results_df = pd.DataFrame(results)
     return results_df