File size: 3,334 Bytes
542f845 |
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 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
import gradio as gr
import requests
# LM Studio REST API base URL
BASE_URL = "http://localhost:1234/api/v0"
# Function to handle chat completions
def chat_with_lmstudio(messages):
url = f"{BASE_URL}/chat/completions"
payload = {
"model": "granite-3.0-2b-instruct", # Replace with the model you have loaded
"messages": messages,
"temperature": 0.7,
"max_tokens": 1024,
"stream": False
}
response = requests.post(url, json=payload)
response.raise_for_status()
response_data = response.json()
return response_data['choices'][0]['message']['content']
# Function to handle text completions
def get_text_completion(prompt):
url = f"{BASE_URL}/completions"
payload = {
"model": "granite-3.0-2b-instruct", # Replace with the model you have loaded
"prompt": prompt,
"temperature": 0.7,
"max_tokens": 100,
"stream": False
}
response = requests.post(url, json=payload)
response.raise_for_status()
response_data = response.json()
return response_data['choices'][0]['text']
# Function to handle text embeddings
def get_text_embedding(text):
url = f"{BASE_URL}/embeddings"
payload = {
"model": "text-embedding-nomic-embed-text-v1.5", # Replace with your embedding model
"input": text
}
response = requests.post(url, json=payload)
response.raise_for_status()
response_data = response.json()
return response_data['data'][0]['embedding']
# Gradio interface for chat
def gradio_chat_interface():
def chat_interface(user_input, history):
# Format history in LM Studio messages format
messages = []
for user_msg, assistant_msg in history:
messages.append({"role": "user", "content": user_msg})
messages.append({"role": "assistant", "content": assistant_msg})
messages.append({"role": "user", "content": user_input})
# Get response from LM Studio
response = chat_with_lmstudio(messages)
# Update history with the assistant's response
history.append((user_input, response))
return history, history
chat_interface = gr.ChatInterface(chat_interface)
chat_interface.launch()
# Gradio interface for text completion
def gradio_text_completion():
gr.Interface(
fn=get_text_completion,
inputs="text",
outputs="text",
title="Text Completion with LM Studio"
).launch()
# Gradio interface for text embedding
def gradio_text_embedding():
gr.Interface(
fn=get_text_embedding,
inputs="text",
outputs="text",
title="Text Embedding with LM Studio"
).launch()
# Main menu to choose the interface
def main():
with gr.Blocks() as demo:
gr.Markdown("""
# LM Studio API Interface
Choose which function you want to use with LM Studio:
""")
with gr.Row():
gr.Button("Chat with Model").click(gradio_chat_interface)
gr.Button("Text Completion").click(gradio_text_completion)
gr.Button("Text Embedding").click(gradio_text_embedding)
demo.launch()
if __name__ == "__main__":
main()
|