mem0/embedchain/notebooks/vertex_ai.ipynb

Cookbook for using VertexAI with Embedchain

Step-1: Install embedchain package

In [ ]:

!pip install embedchain[vertexai]

Step-2: Set VertexAI related environment variables

You can find OPENAI_API_KEY on your OpenAI dashboard.

In [ ]:

import os
from embedchain import App

os.environ["OPENAI_API_KEY"] = "sk-xxx"

Step-3 Create embedchain app and define your config

In [ ]:

app = App.from_config(config={
    "llm": {
        "provider": "vertexai",
        "config": {
            "model": "chat-bison",
            "temperature": 0.5,
            "max_tokens": 1000,
            "stream": False
        }
    },
    "embedder": {
        "provider": "vertexai",
        "config": {
            "model": "textembedding-gecko"
        }
    }
})

Step-4: Add data sources to your app

In [ ]:

app.add("https://www.forbes.com/profile/elon-musk")

Step-5: All set. Now start asking questions related to your data

In [ ]:

while(True):
    question = input("Enter question: ")
    if question in ['q', 'exit', 'quit']:
        break
    answer = app.query(question)
    print(answer)