Update app.py

app.py

@@ -1,30 +1,40 @@
+import requests
+import json
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-# Load your text generation model from Hugging Face using its identifier
-model_identifier = "curiouscurrent/omnicode"
-model = AutoModelForCausalLM.from_pretrained(model_identifier)
-tokenizer = AutoTokenizer.from_pretrained(model_identifier)
-
-def generate_response(input_prompt):
-    # Tokenize input prompt
-    input_ids = tokenizer.encode(input_prompt, return_tensors="pt", max_length=512, truncation=True)
-    
-    # Generate response
-    output_ids = model.generate(input_ids, max_length=100, num_return_sequences=1)
-    response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
-    
-    return response
-
-# Create Gradio interface
-input_prompt = gr.inputs.Textbox(lines=5, label="Input Prompt")
-output_text = gr.outputs.Textbox(label="Response")
-
-gr.Interface(
-    generate_response,
-    inputs=input_prompt,
-    outputs=output_text,
-    title="OmniCode",
-    description="Multi programming coding assistant",
-    theme="compact"
-).launch()
+
+url="https://huggingface.co/curiouscurrent/omnicode"
+
+headers={
+
+    'Content-Type':'application/json'
+}
+
+history=[]
+
+def generate_response(prompt):
+    history.append(prompt)
+    final_prompt="\n".join(history)
+
+    data={
+        "model":"curiouscurrent/omnicode",
+        "prompt":final_prompt,
+        "stream":False
+    }
+
+    response=requests.post(url,headers=headers,data=json.dumps(data))
+
+    if response.status_code==200:
+        response=response.text
+        data=json.loads(response)
+        actual_response=data['response']
+        return actual_response
+    else:
+        print("error:",response.text)
+
+
+interface=gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(lines=4,placeholder="Enter your Prompt"),
+    outputs="text"
+)
+interface.launch()