by Chief Imagineer

Claude 3 Quickstart Chat API

Test this app for free
575
Test this app for free
575 
import logging
import os
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from typing import Optional
import anthropic 

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

app = FastAPI()

client = anthropic.Anthropic(
    api_key=os.environ.get("ANTHROPIC_API_KEY")
)

class ChatRequest(BaseModel):
    system_prompt: Optional[str] = "You are a helpful assistant. Respond to the following question/statement."
    user_prompt: str
    model: Optional[str] = "claude-3-opus-20240229"
    temperature: Optional[float] = 1.0
    max_tokens: Optional[int] = 1000

@app.post("/ask-claude/")
Get full code

Created: | Last Updated:

A Chat API that allows you to immediately integrate any application you're building with the largest anthropic model (Claude Opus) with only your API key. Once you run the app, you can use this app's "/ask-claude" endpoint to send a request to Claude 3 from any application you build.

Introduction to the Template

Welcome to the Claude 3 Quickstart Chat API template! This template allows you to integrate the largest anthropic model, Claude Opus, into any application you're building with just your API key. The /ask-claude endpoint enables you to send requests to Claude 3 and receive responses, making it a powerful tool for various applications.

Getting Started

To get started with this template, click Start with this Template.

Test

After starting with the template, press the Test button. This will begin the deployment of the app and launch the Lazy CLI. The Lazy CLI will guide you through any required user input.

Entering Input

The code does not require any user input through the CLI, so you can skip this section.

Using the App

Once the app is deployed, you can use the /ask-claude endpoint to communicate with the AI. Here’s how you can interact with the API:

  1. Endpoint: /ask-claude/
  2. Method: POST

  3. Request Body: json { "system_prompt": "You are a helpful assistant. Respond to the following question/statement.", "user_prompt": "Your question or statement here", "model": "claude-3-opus-20240229", "temperature": 1.0, "max_tokens": 1000 }

  4. Sample Request: bash curl -X POST "http://<your-server-link>/ask-claude/" -H "Content-Type: application/json" -d '{ "system_prompt": "You are a helpful assistant. Respond to the following question/statement.", "user_prompt": "What is the capital of France?", "model": "claude-3-opus-20240229", "temperature": 1.0, "max_tokens": 1000 }'

  5. Sample Response: json { "message": "The capital of France is Paris." }

Integrating the App

To integrate this app into your service or frontend, follow these steps:

  1. Get the Server Link: After pressing the Test button, the Lazy CLI will provide you with a dedicated server link to use the API.
  2. API Documentation: You will also receive a link to the FastAPI documentation, which you can use to explore and test the endpoints.

Example Integration

If you are integrating this API into another service, you might need to add the server link and endpoints to your external tool. Here’s an example of how to do this:

  • External Tool: Postman
    1. Open Postman and create a new request.
    2. Set the request method to POST.
    3. Enter the server link followed by /ask-claude/ in the request URL.
    4. In the Body tab, select raw and set the type to JSON.
    5. Paste the sample request body into the input field.
    6. Click Send to test the request and view the response.

By following these steps, you can easily integrate the Claude 3 Quickstart Chat API into your application and start leveraging the power of the Claude Opus model.

Technologies

Claude by Anthropic Claude by Anthropic
Python App Templates for Scraping, Machine Learning, Data Science and More Python App Templates for Scraping, Machine Learning, Data Science and More

Similar templates

Add Chatbot to a Website using Flask

A chat interface where users can chat with an AI using the llm ability package on Lazy. This Flask website is meant to simulate a store with dummy data and an AI assistant that a user can talk to about anything using the chat floating button on the bottom right of the page. The chatbox maintains chat history and generates replies with the context of the chat.

Icon 1 Icon 1
360
Stripe Webhook FastAPI Test Sender

By leveraging FastAPI, this template will send and test the mock webhook received from the Stripe API. Stripe Webhook test will print the data on the console.

Icon 1 Icon 1
231
Microsoft Outlook Email Sender App

This app will send an email from your Microsoft account. The recipient, subject, and content of the email are provided by the user. Needs you to generate an app specific password and enter as environment secret along with the username to work.

Icon 1
210
Gmail Email Sender App

This app securely connects to GMAIL via SMPT app and sends a test email. It can be used as a basic building block to build more complicated email sending apps.

Icon 1
187
Weekly Jira Issue Count to Slack

This app fetches Jira issues that had status change in the last week, calculates the count of issues in different issue types, further breaks down each issue type by issue status, prepares a summary for it in form of a table using tabulate, posts the summary in a Slack channel, and schedules the app to run every time the server is started and then every week afterwards. The app requires the following environment variables to be set: - `JIRA_SERVER`: The URL of your Jira server. - `JIRA_USERNAME`: Your Jira username. - `JIRA_API_TOKEN`: Your Jira API token. - `JIRA_PROJECT_NAME`: The name of your Jira project. - `SLACK_TOKEN`: Your Slack token. - `CHANNEL_ID`: The ID of the Slack channel where the summary will be posted.

Icon 1 Icon 1
103
Jira Weekly Done Issues to Slack

This app provides a summary of completed Jira tasks posted to a specific Slack thread every week. It uses the Jira API to download closed tickets from the current week. The query filters for tickets with the status 'Done' and last updated this week. The ticket details, including the ticket URL, are posted to Slack in a single thread. The required environment variables are JIRA_DOMAIN, JIRA_EMAIL, JIRA_API_TOKEN, SLACK_TOKEN, and SLACK_CHANNEL.

Icon 1 Icon 1
80
Timezone Explorer

An app that asks the user to input their timezone and shows the current date and time for the inputted timezone.

51
Send a daily report of some metrics from BigQuery to Slack

This app fetches data from BigQuery using a provided SQL query, formats the data into a table, and posts the table to a specified Slack channel. The data posting is scheduled to happen every day at 10 am UK time.

Icon 1 Icon 1 Icon 1
44
Webflow Collection Item Blog Post Draft API

The Webflow Blog Post Publisher is an app that provides an API endpoint to publish blog posts on Webflow as a draft. The API accepts all necessary information to create a blog post, including the Webflow API token. It also accepts extra fields that will be sent to Webflow as part of the fieldData. The name of the new item added to the collection will be the post_name provided in the request. The slug of the new item will be derived from the post_name by replacing spaces with underscores. The API accepts optional fields in the BlogPostData for extra_fields. All the optional fields will be part of the dictionary extra_fields. All the variables in the extra_fields are converted to kebab-case before they are passed into fieldData. The optional fields inside extra_fields variable are post_body, thumbnail_image, main_image, and post_summary. The app requires two environment variables to function properly: WEBFLOW_API_TOKEN and COLLECTION_ID. The post is linked with the collection in Webflow. The COLLECTION_ID environment variable is the ID of the collection in Webflow where the post will be added.

Icon 1
42