new model

app.py

@@ -1,28 +1,32 @@
-from fastapi import FastAPI
-from transformers import pipeline
- 
-# Create a new FastAPI app instance
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import transformers
+
 app = FastAPI()
- 
-# Initialize the text generation pipeline
-# This function will be able to generate text
-# given an input.
-pipe = pipeline("text2text-generation", 
-model="google/flan-t5-small")
- 
-# Define a function to handle the GET request at `/generate`
-# The generate() function is defined as a FastAPI route that takes a 
-# string parameter called text. The function generates text based on the # input using the pipeline() object, and returns a JSON response 
-# containing the generated text under the key "output"
-@app.get("/generate")
-def generate(text: str):
-    """
-    Using the text2text-generation pipeline from `transformers`, generate text
-    from the given input text. The model used is `google/flan-t5-small`, which
-    can be found [here](<https://huggingface.co/google/flan-t5-small>).
-    """
-    # Use the pipeline to generate text from the given input text
-    output = pipe(text)
-     
-    # Return the generated text in a JSON response
-    return {"output": output[0]["generated_text"]}
+
+model_name = 'Intel/neural-chat-7b-v3-1'
+model = transformers.AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
+
+class ChatInput(BaseModel):
+    system_input: str
+    user_input: str
+
+@app.post("/generate-response")
+async def generate_response(chat_input: ChatInput):
+    try:
+        # Format the input using the provided template
+        prompt = f"### System:\n{chat_input.system_input}\n### User:\n{chat_input.user_input}\n### Assistant:\n"
+
+        # Tokenize and encode the prompt
+        inputs = tokenizer.encode(prompt, return_tensors="pt", add_special_tokens=False)
+
+        # Generate a response
+        outputs = model.generate(inputs, max_length=1000, num_return_sequences=1)
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        # Extract only the assistant's response
+        return {"response": response.split("### Assistant:\n")[-1]}
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

chatui.py

@@ -0,0 +1,36 @@
+import streamlit as st
+import random
+
+
+st.title("💬 Juoksuta AI: R&D LAB")
+
+col1, col2 = st.columns(2)
+
+with col1:
+	if st.button('Tulosta viestiketju.'):
+	    print(st.session_state)
+   
+with col2:
+	if st.button('Tyhjennä viestiketju'):
+	    for key in st.session_state.keys():
+	    	del st.session_state[key]
+
+if "messages" not in st.session_state:
+    st.session_state["messages"] = [{"role": "assistant", "content": "Miten voin auttaa?"}]
+
+for msg in st.session_state.messages:
+    st.chat_message(msg["role"]).write(msg["content"])
+
+msg_bank = ["Aurinko paistaa", "Kuu loistaa", "Tietokone pörisee"]
+
+if prompt := st.chat_input("Kirjoita tähän."):
+   
+ 
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    st.chat_message("user").write(prompt)
+    
+    msg = random.choice(msg_bank)
+    
+    st.session_state.messages.append({"role": "assistant", "content": msg})
+    st.chat_message("assistant").write(msg)
+    

requirements.txt

@@ -1,6 +1,4 @@
 fastapi==0.74.*
 requests==2.27.*
 uvicorn[standard]==0.17.*
-sentencepiece==0.1.*
-torch==1.11.*
 transformers==4.*