robrita

import streamlit as st
import json
import _snowflake
from snowflake.snowpark.context import get_active_session
from snowflake.cortex import complete

# -- Snowflake session --
session = get_active_session()

# -- Page Title --

robrita

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

robrita

<policies>
    <inbound>
        <base />
        <!-- Use a high-limit to calculate usage -->
        <set-variable name="tpmAbsoluteMax" value="@(1000000)" />
        <azure-openai-token-limit tokens-per-minute="@((int)context.Variables["tpmAbsoluteMax"])" counter-key="@(context.Subscription.Id)" estimate-prompt-tokens="true" remaining-tokens-variable-name="tpmRemaining" />
        <!-- Pick the backend based on our TPM usage, the tpmPtuLimit could be set based on subscription ID or anything -->
        <set-variable name="tpmPtuLimit" value="@(1000)" />
        <set-variable name="tpmUsed" value="@(context.Variables.ContainsKey("tpmRemaining") ? (int)context.Variables["tpmAbsoluteMax"] - (int)context.Variables["tpmRemaining"] : 0)" />
        <choose>

robrita

[
  {
    "label": "claude-3-opus-20240229",
    "value": "claude-3-opus-20240229"
  },
  {
    "label": "claude-3-sonnet-20240229",
    "value": "claude-3-sonnet-20240229"
  },
  {

robrita

[
  {
    "label": "llama2-70b-4096",
    "value": "llama2-70b-4096"
  },
  {
    "label": "mixtral-8x7b-32768",
    "value": "mixtral-8x7b-32768"
  },
  {

robrita

[
  {
    "label": "Nous: Capybara 7B (free)",
    "value": "nousresearch/nous-capybara-7b:free"
  },
  {
    "label": "Mistral 7B Instruct (free)",
    "value": "mistralai/mistral-7b-instruct:free"
  },
  {

robrita

{
  "messages": [
    {
      "message": {
        "attachment": {
          "payload": {
            "elements": [
              {
                "title": "I'm Chatalino the #1 ChatGPT Bot for messenger. 👋 Click to join!!",
                "subtitle": "",

robrita

How to use (ChatGPT-like) OpenAI GPT-3 to answer FAQ questions based on your business in Manychat?

(FAQ is hosted in Google Sheets)

👉https://m.me/robrita.me

In this tutorial, we will use the FREE ManychatGPT app for seemless integration.

Summary

1. Create FAQ Dataset

robrita

How to use (ChatGPT-like) OpenAI GPT-3 in Manychat?

(Very First Tutorial using External Request)

👉https://m.me/robrita.me

Summary

1. Get OpenAI API Key
2. Go to Manychat, add External Request block inside the Default Reply
3. Paste the request details