ranfysvalle02

from langgraph.store.mongodb import MongoDBStore
from pymongo.collection import Collection
from pymongo.database import Database
from pymongo import MongoClient
import os
from langgraph.checkpoint.mongodb import MongoDBSaver
from dotenv import load_dotenv
from langchain_openai import AzureOpenAIEmbeddings
from langchain_openai import AzureChatOpenAI

ranfysvalle02

/**    
 * Main function to get comments from the active Google Document, send them to the Azure OpenAI API, and log the responses.    
 */    
function respondToComments() {    
  try {    
    // Get the active document and its ID    
    var doc = DocumentApp.getActiveDocument();    
    var documentId = doc.getId();    
  
    // Get the body text of the document    

ranfysvalle02

function getComments() {  
  try {  
    var doc = DocumentApp.getActiveDocument();  
    var documentId = doc.getId();  

    var fields = 'comments(author/displayName,content,createdTime),nextPageToken';  
    var pageToken = null;  
    var comments = [];  

    do {  

ranfysvalle02

# Import necessary libraries
from langgraph.graph import StateGraph, END
from typing import Dict, TypedDict, Optional, Literal, List, Union

# Define Graph State
class GraphState(TypedDict):
    init_input: Optional[str] = None
    fruit: Optional[str] = None
    final_result: Optional[str] = None
    user_confirmation: Optional[str] = None

ranfysvalle02

from unstructured.partition.auto import partition
import pymongo
from openai import AzureOpenAI

az_client = AzureOpenAI(azure_endpoint="",api_version="",api_key="")
def generate_embeddings(text, model=""): # model = "deployment_name"
    return az_client.embeddings.create(input = [text], model=model).data[0].embedding

MDB_URI = ""
DB_NAME = ""

ranfysvalle02

import json
import requests

def get_repo_info(owner, repo):
    url = f"https://api.github.com/repos/{owner}/{repo}"
    headers = {"Accept": "application/vnd.github+json"}
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.json()
    else:

ranfysvalle02

from openai import AzureOpenAI
import os
import subprocess
import json 
from shutil import rmtree

# Azure OpenAI configuration
azure_openai_endpoint = os.getenv('OPENAI_AZURE_ENDPOINT', '')
azure_openai_api_key = os.getenv('OPENAI_API_KEY', '')
azure_openai_deployment_id = ''

ranfysvalle02

from openai import AzureOpenAI
import os
import subprocess
import json 
from shutil import rmtree

# Azure OpenAI configuration
azure_openai_endpoint = os.getenv('OPENAI_AZURE_ENDPOINT', '')
azure_openai_api_key = os.getenv('OPENAI_API_KEY', '')
azure_openai_deployment_id = ''

ranfysvalle02

from youtube_transcript_api import YouTubeTranscriptApi
from duckduckgo_search import DDGS
from openai import AzureOpenAI

# Replace with your actual values
AZURE_OPENAI_ENDPOINT = "https://DEMO.openai.azure.com"
AZURE_OPENAI_API_KEY = "" 
deployment_name = "gpt-4-32k"  # The name of your model deployment
client = AzureOpenAI(azure_endpoint=AZURE_OPENAI_ENDPOINT,api_version="2023-07-01-preview",api_key=AZURE_OPENAI_API_KEY)
# Replace with your actual values - if desired

ranfysvalle02

from elevenlabs.client import ElevenLabs
from elevenlabs import play
from langchain_community.vectorstores import MongoDBAtlasVectorSearch
from langchain_openai import AzureOpenAIEmbeddings
from langchain_core.messages import HumanMessage
from langchain_openai import AzureChatOpenAI
import pymongo
# PDF loaded into MongoDB Atlas = https://arxiv.org/pdf/2303.08774.pdf
MDB_URI = ""
cluster = pymongo.MongoClient(MDB_URI)