Subindo arquivos

README.md

@@ -1,13 +1,37 @@
 ---
-title: My Llama3.1 Groq
-emoji: 🐠
-colorFrom: green
+title: My-Llama3.1-Groq
+emoji: 🦙🤖🆙
+colorFrom: blue
 colorTo: green
 sdk: gradio
-sdk_version: 4.41.0
+sdk_version: "4.12.0"
 app_file: app.py
 pinned: false
-license: ecl-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+## This Project
+
+This project is a chatbot powered by the Groq Cloud API using the `Llama-3.1-70b-versatile` model.
+
+This chatbot leverages the capabilities of Groq's cloud API, specifically utilizing the advanced `Llama-3.1-70b-versatile` model to provide efficient and accurate responses. The interface is built using Gradio, allowing for easy interaction and deployment.
+
+## More Information
+
+- **Developer:** Ramon Mayor Martins, Ph.D. (2024)
+- **Email:** rmayormartins at: gmail.com
+- **Homepage:** [rmayormartins.github.io](https://rmayormartins.github.io/)
+- **Twitter:** [@rmayormartins](https://twitter.com/rmayormartins)
+- **GitHub:** [rmayormartins](https://github.com/rmayormartins)
+
+## Special Thanks
+
+A special thank you to:
+
+- **Meta** for developing the Llama models. Learn more at [Llama 3](https://llama.meta.com/llama3/).
+- **Groq** for providing the powerful cloud API that makes this project possible. Visit [Groq](https://groq.com/) for more information.
+- **Federal Institute of Santa Catarina (IFSC)** [IFSC](https://www.ifsc.edu.br/)
+
+---
+
+Feel free to explore, interact, and contribute!

app.py

@@ -0,0 +1,52 @@
+import os
+from groq import Groq
+import gradio as gr
+
+#
+api_key = os.getenv("GROQ_API_KEY2")
+
+#
+client = Groq(api_key=api_key)
+
+# 
+system_prompt = {
+    "role": "system",
+    "content": "You are a useful assistant. You reply with efficient answers."
+}
+
+# 
+async def chat_groq(message, history):
+    messages = [system_prompt]
+    
+    for msg in history:
+        messages.append({"role": "user", "content": str(msg[0])})
+        messages.append({"role": "assistant", "content": str(msg[1])})
+        
+    messages.append({"role": "user", "content": str(message)})
+    
+    response_content = ''
+    
+    # modelo `llama-3.1-70b-versatile`
+    stream = client.chat.completions.create(
+        model="llama-3.1-70b-versatile",
+        messages=messages,
+        max_tokens=1024,
+        temperature=1.3,
+        stream=True
+    )
+
+    for chunk in stream:
+        content = chunk.choices[0].delta.content
+        if content:
+            response_content += chunk.choices[0].delta.content 
+        yield response_content
+
+# Interface Gradio
+with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
+    gr.ChatInterface(chat_groq,
+                     clear_btn=None, 
+                     undo_btn=None, 
+                     retry_btn=None)
+
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+groq
+gradio==4.29.0
+transformers
+torch