Upload 3 files

Dockerfile

@@ -1,13 +1,25 @@
-FROM python:3.12
-
-WORKDIR /code
-
-COPY ./requirements.txt /code/requirements.txt
-
-RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
-
-COPY . .
-
-EXPOSE 7860
-
-CMD ["shiny", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]
+# Use Python 3.11 slim image
+FROM python:3.11-slim
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y git wget && rm -rf /var/lib/apt/lists/*
+
+# Create a non-root user
+RUN useradd -m appuser
+USER appuser
+
+# Set working directory
+WORKDIR /app
+
+# Copy and install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy app files
+COPY . .
+
+# Expose port 8000 for FastAPI
+EXPOSE 8000
+
+# Start FastAPI server
+CMD ["python", "app.py"]

app.py

@@ -1,162 +1,93 @@
-import faicons as fa
-import plotly.express as px
-
-# Load data and compute static values
-from shared import app_dir, tips
-from shinywidgets import render_plotly
-
-from shiny import reactive, render
-from shiny.express import input, ui
-
-bill_rng = (min(tips.total_bill), max(tips.total_bill))
-
-# Add page title and sidebar
-ui.page_opts(title="Restaurant tipping", fillable=True)
-
-with ui.sidebar(open="desktop"):
-    ui.input_slider(
-        "total_bill",
-        "Bill amount",
-        min=bill_rng[0],
-        max=bill_rng[1],
-        value=bill_rng,
-        pre="$",
-    )
-    ui.input_checkbox_group(
-        "time",
-        "Food service",
-        ["Lunch", "Dinner"],
-        selected=["Lunch", "Dinner"],
-        inline=True,
-    )
-    ui.input_action_button("reset", "Reset filter")
-
-# Add main content
-ICONS = {
-    "user": fa.icon_svg("user", "regular"),
-    "wallet": fa.icon_svg("wallet"),
-    "currency-dollar": fa.icon_svg("dollar-sign"),
-    "ellipsis": fa.icon_svg("ellipsis"),
-}
-
-with ui.layout_columns(fill=False):
-    with ui.value_box(showcase=ICONS["user"]):
-        "Total tippers"
-
-        @render.express
-        def total_tippers():
-            tips_data().shape[0]
-
-    with ui.value_box(showcase=ICONS["wallet"]):
-        "Average tip"
-
-        @render.express
-        def average_tip():
-            d = tips_data()
-            if d.shape[0] > 0:
-                perc = d.tip / d.total_bill
-                f"{perc.mean():.1%}"
-
-    with ui.value_box(showcase=ICONS["currency-dollar"]):
-        "Average bill"
-
-        @render.express
-        def average_bill():
-            d = tips_data()
-            if d.shape[0] > 0:
-                bill = d.total_bill.mean()
-                f"${bill:.2f}"
-
-
-with ui.layout_columns(col_widths=[6, 6, 12]):
-    with ui.card(full_screen=True):
-        ui.card_header("Tips data")
-
-        @render.data_frame
-        def table():
-            return render.DataGrid(tips_data())
-
-    with ui.card(full_screen=True):
-        with ui.card_header(class_="d-flex justify-content-between align-items-center"):
-            "Total bill vs tip"
-            with ui.popover(title="Add a color variable", placement="top"):
-                ICONS["ellipsis"]
-                ui.input_radio_buttons(
-                    "scatter_color",
-                    None,
-                    ["none", "sex", "smoker", "day", "time"],
-                    inline=True,
-                )
-
-        @render_plotly
-        def scatterplot():
-            color = input.scatter_color()
-            return px.scatter(
-                tips_data(),
-                x="total_bill",
-                y="tip",
-                color=None if color == "none" else color,
-                trendline="lowess",
-            )
-
-    with ui.card(full_screen=True):
-        with ui.card_header(class_="d-flex justify-content-between align-items-center"):
-            "Tip percentages"
-            with ui.popover(title="Add a color variable"):
-                ICONS["ellipsis"]
-                ui.input_radio_buttons(
-                    "tip_perc_y",
-                    "Split by:",
-                    ["sex", "smoker", "day", "time"],
-                    selected="day",
-                    inline=True,
-                )
-
-        @render_plotly
-        def tip_perc():
-            from ridgeplot import ridgeplot
-
-            dat = tips_data()
-            dat["percent"] = dat.tip / dat.total_bill
-            yvar = input.tip_perc_y()
-            uvals = dat[yvar].unique()
-
-            samples = [[dat.percent[dat[yvar] == val]] for val in uvals]
-
-            plt = ridgeplot(
-                samples=samples,
-                labels=uvals,
-                bandwidth=0.01,
-                colorscale="viridis",
-                colormode="row-index",
-            )
-
-            plt.update_layout(
-                legend=dict(
-                    orientation="h", yanchor="bottom", y=1.02, xanchor="center", x=0.5
-                )
-            )
-
-            return plt
-
-
-ui.include_css(app_dir / "styles.css")
-
-# --------------------------------------------------------
-# Reactive calculations and effects
-# --------------------------------------------------------
-
-
-@reactive.calc
-def tips_data():
-    bill = input.total_bill()
-    idx1 = tips.total_bill.between(bill[0], bill[1])
-    idx2 = tips.time.isin(input.time())
-    return tips[idx1 & idx2]
-
-
-@reactive.effect
-@reactive.event(input.reset)
-def _():
-    ui.update_slider("total_bill", value=bill_rng)
-    ui.update_checkbox_group("time", selected=["Lunch", "Dinner"])
+from peft import AutoPeftModelForCausalLM
+import asyncio
+from fastapi import FastAPI
+import uvicorn
+import os
+import nest_asyncio
+import socket
+import json
+from transformers import pipeline, AutoTokenizer
+import time
+import torch
+import requests
+app = FastAPI()
+model_ask = AutoPeftModelForCausalLM.from_pretrained(
+    "robertthecreator/assistant-chatbot",
+    device_map="auto",
+    torch_dtype=torch.float16
+)
+tokenizer_ask = AutoTokenizer.from_pretrained("robertthecreator/assistant-chatbot")
+tokenizer_ask.pad_token = tokenizer_ask.eos_token
+model_ask.eval()
+api_key = os.getenv("TAVILY_API_KEY", "default-key")
+
+def get_from_web(query, k=3):
+    context = ""
+    response = requests.post(
+        "https://api.tavily.com/search",
+        headers={"Content-Type": "application/json"},
+        json={"query": query, "api_key": api_key}
+    )
+    data = response.json()
+    for result in data["results"]:
+        print(result["content"])
+        context += result["content"] + "\n"
+    return context
+
+
+@app.post("/ask")
+def ask(text: str):
+    global context
+    print("starting...")
+    context = """You're an AI assistant designed to help me with every day task, productivity and engineering. Youre name is JARVIS. Use the context you have to answer any questions."""
+    context = get_from_web(text) + "\n" + context
+    print(context)
+    formatted_prompt = f"""CONTEXT: {context}\nPROMPTER: {text}\nASSISTANT:"""
+    inputs = tokenizer_ask(formatted_prompt, return_tensors="pt").to(model_ask.device)
+
+    with torch.no_grad():
+        outputs = model_ask.generate(
+            **inputs,
+            max_new_tokens=250,
+            temperature=0.7,
+            top_p=0.9,
+            top_k=50,
+            repetition_penalty=1.2,
+            do_sample=True,
+            pad_token_id=tokenizer_ask.eos_token_id,
+            eos_token_id=tokenizer_ask.eos_token_id,
+            early_stopping=True
+        )
+
+
+    response = tokenizer_ask.decode(outputs[0], skip_special_tokens=True)
+    print(response)
+
+    if "ASSISTANT:" in response:
+        response = response.split("ASSISTANT:")[-1].strip()
+
+    response = response.split('\r')[0]
+    response = response.split('PROMPTER')[0]
+    response = response.split('ROLE:')[0]
+    response = response.split('<|user|>')[0]
+    response = response.split('User:')[0]
+
+    return response
+
+async def start():
+    s = socket.socket()
+    s.bind(('', 0))
+    port = s.getsockname()[1]
+    s.close()
+
+    config = uvicorn.Config(
+        app,
+        host="0.0.0.0",
+        port=port,
+        log_level="info"
+    )
+    server = uvicorn.Server(config)
+
+    await server.serve()
+
+uvicorn.run(app, host="0.0.0.0", port=8000, log_level="info")

requirements.txt

@@ -1,6 +1,7 @@
-faicons
-shiny
-shinywidgets
-plotly
-pandas
-ridgeplot
+fastapi
+uvicorn[standard]
+torch
+transformers
+peft
+requests
+nest_asyncio