Update app.py

app.py

@@ -1,61 +1,36 @@
+# Import necessary libraries
 import streamlit as st
-from huggingface_hub import InferenceClient
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient()
+# Load the model and tokenizer
+model_name = "mistralai/Codestral-22B-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    messages = [{"role": "system", "content": system_message}]
-    for user_msg, assistant_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if assistant_msg:
-            messages.append({"role": "assistant", "content": assistant_msg})
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-    try:
-        for message in client.chat_completion(
-            model="mistralai/Codestral-22B-v0.1",
-            messages=messages,
-            max_tokens=max_tokens,
-            stream=True,
-            temperature=temperature,
-            top_p=top_p,
-        ):
-            token = message.choices[0].delta.content
-            response += token
-            yield response
-    except Exception as e:
-        yield f"Error: {e}"
+# Initialize the pipeline
+text_generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 # Streamlit interface
-st.title("Chat with Codestral Model")
-system_message = st.text_input("System message", value="You are an expert python coder with in-depth knowledge of langchain.")
-max_tokens = st.slider("Max new tokens", min_value=1, max_value=2048, value=2048, step=1)
-temperature = st.slider("Temperature", min_value=0.0, max_value=1.0, value=0.6, step=0.1)
-top_p = st.slider("Top-p (nucleus sampling)", min_value=0.1, max_value=1.0, value=0.95, step=0.05)
-
-# Initialize history in session state
-if "history" not in st.session_state:
-    st.session_state.history = []
+st.title("Codestral Text Generation")
 
-def get_response():
-    user_input = st.session_state.user_input
-    if user_input:
-        st.session_state.history.append((user_input, ""))
-        response_generator = respond(user_input, st.session_state.history, system_message, max_tokens, temperature, top_p)
-        response = ""
-        for r in response_generator:
-            response = r
-        st.session_state.history[-1] = (user_input, response)
-        st.session_state.user_input = ""  # Clear input after sending
-
-# Display chat history
-st.text_area("Chat History", value="\n".join([f"User: {h[0]}\nAssistant: {h[1]}" for h in st.session_state.history]), height=300, key="chat_history")
+st.write("""
+This is a text generation application using the Codestral model from Mistral AI.
+Enter your prompt below and generate text.
+""")
 
 # User input
-st.text_input("Your message:", key="user_input", on_change=get_response)
+user_input = st.text_area("Enter your prompt here:", "")
 
+if st.button("Generate"):
+    if user_input:
+        with st.spinner("Generating text..."):
+            # Generate text using the model
+            generated_text = text_generator(user_input, max_length=100, num_return_sequences=1)
+            st.write("### Generated Text")
+            st.write(generated_text[0]['generated_text'])
+    else:
+        st.warning("Please enter a prompt to generate text.")
+
+# Run the Streamlit app
+if __name__ == '__main__':
+    st.run()