Upload 3 files
Browse files- Dockerfile +17 -0
- app.py +67 -0
- requirements.txt +7 -0
Dockerfile
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM python:3.10-slim
|
| 2 |
+
|
| 3 |
+
WORKDIR /app
|
| 4 |
+
|
| 5 |
+
# System deps
|
| 6 |
+
RUN apt-get update && apt-get install -y \
|
| 7 |
+
git \
|
| 8 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 9 |
+
|
| 10 |
+
COPY requirements.txt .
|
| 11 |
+
RUN pip install --no-cache-dir -r requirements.txt
|
| 12 |
+
|
| 13 |
+
COPY app.py .
|
| 14 |
+
|
| 15 |
+
EXPOSE 7860
|
| 16 |
+
|
| 17 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
app.py
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI
|
| 2 |
+
from pydantic import BaseModel
|
| 3 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 4 |
+
import torch
|
| 5 |
+
|
| 6 |
+
MODEL_ID = "meta-llama/Meta-Llama-3.1-8B-Instruct"
|
| 7 |
+
|
| 8 |
+
app = FastAPI(title="Artist Description Generator")
|
| 9 |
+
|
| 10 |
+
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
| 11 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 12 |
+
MODEL_ID,
|
| 13 |
+
device_map="auto",
|
| 14 |
+
torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
|
| 15 |
+
load_in_4bit=torch.cuda.is_available()
|
| 16 |
+
)
|
| 17 |
+
|
| 18 |
+
class ArtistInput(BaseModel):
|
| 19 |
+
artist_name: str
|
| 20 |
+
country: str | None = None
|
| 21 |
+
genres: list[str] = []
|
| 22 |
+
top_tracks: list[str] = []
|
| 23 |
+
metrics: dict = {}
|
| 24 |
+
|
| 25 |
+
def build_prompt(data: ArtistInput) -> str:
|
| 26 |
+
return f"""
|
| 27 |
+
You are writing a factual artist description for a music analytics platform.
|
| 28 |
+
|
| 29 |
+
Rules:
|
| 30 |
+
- Use ONLY the provided data
|
| 31 |
+
- Do NOT invent awards, numbers, or events
|
| 32 |
+
- If data is missing, omit it
|
| 33 |
+
- Keep it concise and neutral
|
| 34 |
+
- 3–5 sentences maximum
|
| 35 |
+
|
| 36 |
+
Artist name: {data.artist_name}
|
| 37 |
+
Country: {data.country}
|
| 38 |
+
Genres: {", ".join(data.genres)}
|
| 39 |
+
Top tracks: {", ".join(data.top_tracks)}
|
| 40 |
+
Metrics: {data.metrics}
|
| 41 |
+
|
| 42 |
+
Artist description:
|
| 43 |
+
""".strip()
|
| 44 |
+
|
| 45 |
+
@app.post("/generate")
|
| 46 |
+
def generate_description(data: ArtistInput):
|
| 47 |
+
prompt = build_prompt(data)
|
| 48 |
+
|
| 49 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 50 |
+
|
| 51 |
+
with torch.no_grad():
|
| 52 |
+
output = model.generate(
|
| 53 |
+
**inputs,
|
| 54 |
+
max_new_tokens=180,
|
| 55 |
+
temperature=0.3,
|
| 56 |
+
top_p=0.9,
|
| 57 |
+
do_sample=True
|
| 58 |
+
)
|
| 59 |
+
|
| 60 |
+
text = tokenizer.decode(output[0], skip_special_tokens=True)
|
| 61 |
+
|
| 62 |
+
description = text.split("Artist description:")[-1].strip()
|
| 63 |
+
|
| 64 |
+
return {
|
| 65 |
+
"artist": data.artist_name,
|
| 66 |
+
"description": description
|
| 67 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
fastapi
|
| 2 |
+
uvicorn
|
| 3 |
+
transformers
|
| 4 |
+
torch
|
| 5 |
+
accelerate
|
| 6 |
+
bitsandbytes
|
| 7 |
+
pydantic
|