API
If you're looking for an API, you can choose from your desired programming language.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
const axios = require('axios');
const fs = require('fs');
const path = require('path');
// helper function to help you convert your local images into base64 format
async function toB64(imgPath) {
const data = fs.readFileSync(path.resolve(imgPath));
return Buffer.from(data).toString('base64');
}
const api_key = "YOUR API-KEY";
const url = "https://api.segmind.com/v1/claude-3.7-sonnet";
const data = {
"instruction": "Respond in a playful and humorous manner, keeping the tone light and entertaining.",
"temperature": 0.1,
"messages": [
{
"role": "user",
"content": "tell me a joke on cats"
},
{
"role": "assistant",
"content": "here is a joke about cats..."
},
{
"role": "user",
"content": "now a joke on dogs"
}
]
};
(async function() {
try {
const response = await axios.post(url, data, { headers: { 'x-api-key': api_key } });
console.log(response.data);
} catch (error) {
console.error('Error:', error.response.data);
}
})();Attributes
System prompt to give the LLM some context
Randomness variable between 0 - 1.
An array of objects containing the role and content
Could be "user", "assistant" or "system".
A string containing the user's query or the assistant's response.
To keep track of your credit usage, you can inspect the response headers of each API call. The x-remaining-credits property will indicate the number of remaining credits in your account. Ensure you monitor this value to avoid any disruptions in your API usage.
Claude 3.7 Sonnet
Claude 3.7 Sonnet is Anthropic's most intelligent model to date, excelling in coding, content generation, data analysis, and planning. It's the first hybrid reasoning model, combining the capabilities of an ordinary LLM with extended thinking for improved accuracy.
Key Features of Claude 3.7 Sonnet
-
State-of-the-art Coding: Claude 3.7 Sonnet is designed for agentic coding, covering the entire software development lifecycle from planning to maintenance. It supports up to 128K output tokens, which is valuable for code generation and planning.
-
Computer Use: Integrate Claude 3.7 Sonnet via API to enable it to use computers like humans. It can look at a screen, move a cursor, click buttons, and type text to automate repetitive tasks, perform software testing, and conduct research.
-
Advanced Reasoning: With enhanced reasoning capabilities, Claude 3.7 Sonnet can understand nuanced instructions and context, recognize and correct its own mistakes, and create sophisticated analyses from complex data.
-
Knowledge Q&A: Its large context window and low hallucination rates make it ideal for answering questions around large knowledge bases, documents, and codebases.
-
Visual Data Extraction: Claude 3.7 Sonnet can extract information from visuals like charts, graphs, and complex diagrams, making it suitable for data analytics and data science tasks.
-
Content Generation and Analysis: It excels at writing and can understand nuance and tone to generate compelling content and analyze content on a deeper leve
Use cases
-
Software Development: Assist in coding, debugging, and optimizing software projects.
-
Advanced Chatbots: Create chatbots that connect data across systems with a human-like tone.
-
Data Analytics: Extract insights from visual data like charts and graphs.
-
Robotic Process Automation: Automate repetitive tasks and complex processes.
Other Popular Models
sdxl-img2img
SDXL Img2Img is used for text-guided image-to-image translation. This model uses the weights from Stable Diffusion to generate new images from an input image using StableDiffusionImg2ImgPipeline from diffusers
sdxl-controlnet
SDXL ControlNet gives unprecedented control over text-to-image generation. SDXL ControlNet models Introduces the concept of conditioning inputs, which provide additional information to guide the image generation process
face-to-many
Turn a face into 3D, emoji, pixel art, video game, claymation or toy
codeformer
CodeFormer is a robust face restoration algorithm for old photos or AI-generated faces.
