import io from starlette import status from functions import * from PyPDF2 import PdfReader import pandas as pd from fastapi import FastAPI, File, UploadFile, HTTPException from pydantic import BaseModel from fastapi.middleware.cors import CORSMiddleware from langchain_community.document_loaders import UnstructuredURLLoader from src.api.speech_api import speech_translator_router from functions import client as supabase from urllib.parse import urlparse import nltk nltk.download('punkt_tab') app = FastAPI(title="ConversAI", root_path="/api/v1") app.add_middleware( CORSMiddleware, allow_origins=["*"], allow_credentials=True, allow_methods=["*"], allow_headers=["*"], ) app.include_router(speech_translator_router, prefix="/speech") @app.post("/signup") async def sign_up(email, username, password): res, _ = supabase.auth.sign_up( {"email": email, "password": password, "role": "user"} ) user_id = res[1].id r_ = createUser(user_id=user_id, username=username) print(r_) response = { "status": "success", "code": 200, "message": "Please check you email address for email verification", } return response @app.post("/session-check") async def check_session(): res = supabase.auth.get_session() return res @app.post("/get-user") async def get_user(access_token): res = supabase.auth.get_user(jwt=access_token) return res @app.post("/referesh-token") async def refresh_token(refresh_token): res = supabase.auth.refresh_token(refresh_token) return res @app.post("/login") async def sign_in(email, password): try: res = supabase.auth.sign_in_with_password( {"email": email, "password": password} ) user_id = res.user.id access_token = res.session.access_token refresh_token = res.session.refresh_token store_session_check = supabase.table("Stores").select("*").filter("StoreID", "eq", user_id).execute() store_id = None if store_session_check and store_session_check.data: store_id = store_session_check.data[0].get("StoreID") userData = client.table("ConversAI_UserInfo").select("*").filter("user_id", "eq", user_id).execute().data username = userData[0]["username"] if not store_id: response = ( supabase.table("Stores").insert( { "AccessToken": access_token, "StoreID": user_id, "RefreshToken": refresh_token, } ).execute() ) message = { "message": "Success", "code": status.HTTP_200_OK, "username": username, "user_id": user_id, "access_token": access_token, "refresh_token": refresh_token, } return message elif store_id == user_id: raise HTTPException( status_code=status.HTTP_400_BAD_REQUEST, detail="You are already signed in. Please sign out first to sign in again." ) else: raise HTTPException( status_code=status.HTTP_400_BAD_REQUEST, detail="Failed to sign in. Please check your credentials." ) except HTTPException as http_exc: raise http_exc except Exception as e: raise HTTPException( status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=f"An unexpected error occurred during sign-in: {str(e)}" ) @app.post('login_with_token') async def login_with_token(token): try: res = supabase.auth.sign_in_with_id_token(token) print(res) user_id = res.user.id access_token = res.session.access_token refresh_token = res.session.refresh_token store_session_check = supabase.table("Stores").select("*").filter("StoreID", "eq", user_id).execute() store_id = None if store_session_check and store_session_check.data: store_id = store_session_check.data[0].get("StoreID") if not store_id: response = ( supabase.table("Stores").insert( { "AccessToken": access_token, "StoreID": user_id, "RefreshToken": refresh_token, } ).execute() ) message = { "message": "Success", "code": status.HTTP_200_OK, "user_id": user_id, "access_token": access_token, "refresh_token": refresh_token } return message elif store_id == user_id: raise HTTPException( status_code=status.HTTP_400_BAD_REQUEST, detail="You are already signed in. Please sign out first to sign in again." ) else: raise HTTPException( status_code=status.HTTP_400_BAD_REQUEST, detail="Failed to sign in. Please check your credentials." ) except HTTPException as http_exc: raise http_exc except Exception as e: raise HTTPException( status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=f"An unexpected error occurred during sign-in: {str(e)}" ) @app.post("/set-session-data") async def set_session_data(access_token, refresh_token): res = supabase.auth.set_session(access_token, refresh_token) return res @app.post("/logout") async def sign_out(user_id): try: supabase.table("Stores").delete().eq( "StoreID", user_id ).execute() res = supabase.auth.sign_out() response = {"message": "success"} return response except Exception as e: raise HTTPException(status_code=400, detail=str(e)) @app.post("/oauth") async def oauth(provider): res = supabase.auth.sign_in_with_oauth({"provider": provider}) return res @app.post("/newChatbot") async def newChatbot(chatbotName: str, username: str): currentBotCount = len(listTables(username=username)["output"]) limit = client.table("ConversAI_UserConfig").select("chatbotLimit").eq("user_id", username).execute().data[0][ "chatbotLimit"] if currentBotCount >= int(limit): return { "output": "CHATBOT LIMIT EXCEEDED" } client.table("ConversAI_ChatbotInfo").insert({"user_id": username, "chatbotname": chatbotName}).execute() chatbotName = f"convai${username}${chatbotName}" return createTable(tablename=chatbotName) @app.post("/addPDF") async def addPDFData(vectorstore: str, pdf: UploadFile = File(...)): source = pdf.filename pdf = await pdf.read() with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as temp_file: temp_file.write(pdf) temp_file_path = temp_file.name loader = PDFMinerLoader(file_path = temp_file_path, concatenate_pages = True) text = loader.load()[0].page_content os.remove(temp_file_path) username, chatbotname = vectorstore.split("$")[1], vectorstore.split("$")[2] df = pd.DataFrame(client.table("ConversAI_ChatbotInfo").select("*").execute().data) currentCount = df[(df["user_id"] == username) & (df["chatbotname"] == chatbotname)]["charactercount"].iloc[0] limit = client.table("ConversAI_UserConfig").select("tokenLimit").eq("user_id", username).execute().data[0][ "tokenLimit"] newCount = currentCount + len(text) if newCount < int(limit): client.table("ConversAI_ChatbotInfo").update({"charactercount": str(newCount)}).eq("user_id", username).eq( "chatbotname", chatbotname).execute() return addDocuments(text=text, source=source, vectorstore=vectorstore) else: return { "output": "DOCUMENT EXCEEDING LIMITS, PLEASE TRY WITH A SMALLER DOCUMENT." } @app.post("/scanAndReturnText") async def returnText(pdf: UploadFile = File(...)): pdf = await pdf.read() text = getTextFromImagePDF(pdfBytes=pdf) return text @app.post("/addText") async def addText(vectorstore: str, text: str): username, chatbotname = vectorstore.split("$")[1], vectorstore.split("$")[2] df = pd.DataFrame(client.table("ConversAI_ChatbotInfo").select("*").execute().data) currentCount = df[(df["user_id"] == username) & (df["chatbotname"] == chatbotname)]["charactercount"].iloc[0] newCount = currentCount + len(text) limit = client.table("ConversAI_UserConfig").select("tokenLimit").eq("user_id", username).execute().data[0][ "tokenLimit"] if newCount < int(limit): client.table("ConversAI_ChatbotInfo").update({"charactercount": str(newCount)}).eq("user_id", username).eq( "chatbotname", chatbotname).execute() return addDocuments(text=text, source="text", vectorstore=vectorstore) else: return { "output": "WEBSITE EXCEEDING LIMITS, PLEASE TRY WITH A SMALLER DOCUMENT." } class AddQAPair(BaseModel): vectorstore: str question: str answer: str @app.post("/addQAPair") async def addText(addQaPair: AddQAPair): username, chatbotname = addQaPair.vectorstore.split("$")[1], addQaPair.vectorstore.split("$")[2] df = pd.DataFrame(client.table("ConversAI_ChatbotInfo").select("*").execute().data) currentCount = df[(df["user_id"] == username) & (df["chatbotname"] == chatbotname)]["charactercount"].iloc[0] qa = f"QUESTION: {addQaPair.question}\tANSWER: {addQaPair.answer}" newCount = currentCount + len(qa) limit = client.table("ConversAI_UserConfig").select("tokenLimit").eq("user_id", username).execute().data[0][ "tokenLimit"] if newCount < int(limit): client.table("ConversAI_ChatbotInfo").update({"charactercount": str(newCount)}).eq("user_id", username).eq( "chatbotname", chatbotname).execute() return addDocuments(text=qa, source="Q&A Pairs", vectorstore=addQaPair.vectorstore) else: return { "output": "WEBSITE EXCEEDING LIMITS, PLEASE TRY WITH A SMALLER DOCUMENT." } @app.post("/addWebsite") async def addWebsite(vectorstore: str, websiteUrls: list[str]): loader = UnstructuredURLLoader(urls=websiteUrls) docs = loader.load() text = "\n\n".join( [f"{docs[doc].page_content}" for doc in range(len(docs))] ) username, chatbotname = vectorstore.split("$")[1], vectorstore.split("$")[2] df = pd.DataFrame(client.table("ConversAI_ChatbotInfo").select("*").execute().data) currentCount = df[(df["user_id"] == username) & (df["chatbotname"] == chatbotname)]["charactercount"].iloc[0] newCount = currentCount + len(text) limit = client.table("ConversAI_UserConfig").select("tokenLimit").eq("user_id", username).execute().data[0][ "tokenLimit"] if newCount < int(limit): client.table("ConversAI_ChatbotInfo").update({"charactercount": str(newCount)}).eq("user_id", username).eq( "chatbotname", chatbotname).execute() return addDocuments(text=text, source=urlparse(websiteUrls[0]).netloc, vectorstore=vectorstore) else: return { "output": "WEBSITE EXCEEDING LIMITS, PLEASE TRY WITH A SMALLER DOCUMENT." } @app.post("/answerQuery") async def answerQuestion(query: str, vectorstore: str, llmModel: str = "llama3-70b-8192"): return answerQuery(query=query, vectorstore=vectorstore, llmModel=llmModel) @app.post("/deleteChatbot") async def delete(chatbotName: str): username, chatbotName = chatbotName.split("$")[1], chatbotName.split("$")[2] client.table('ConversAI_ChatbotInfo').delete().eq('user_id', username).eq('chatbotname', chatbotName).execute() return deleteTable(tableName=chatbotName) @app.post("/listChatbots") async def delete(username: str): return listTables(username=username) @app.post("/getLinks") async def crawlUrl(baseUrl: str): return { "urls": getLinks(url=baseUrl, timeout=30) } @app.post("/getCurrentCount") async def getCount(vectorstore: str): username, chatbotName = vectorstore.split("$")[1], vectorstore.split("$")[2] df = pd.DataFrame(client.table("ConversAI_ChatbotInfo").select("*").execute().data) return { "currentCount": df[(df['user_id'] == username) & (df['chatbotname'] == chatbotName)]['charactercount'].iloc[0] } @app.post("/getYoutubeTranscript") async def getYTTranscript(urls: str): return { "transcript": getTranscript(urls=urls) } @app.post("/analyzeData") async def analyzeAndAnswer(query: str, file: UploadFile = File(...)): extension = file.filename.split(".")[-1] try: if extension in ["xls", "xlsx", "xlsm", "xlsb"]: df = pd.read_excel(io.BytesIO(await file.read())) response = analyzeData(query=query, dataframe=df) elif extension == "csv": df = pd.read_csv(io.BytesIO(await file.read())) response = analyzeData(query=query, dataframe=df) else: response = "INVALID FILE TYPE" return { "output": response } except: return { "output": "UNABLE TO ANSWER QUERY" }