Upload 4 files

Dockerfile

@@ -1,3 +1,27 @@
-FROM ollama/ollama
+FROM python:3.10-slim
 
-COPY ./pull-llama3.sh /pull-llama3.sh
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && apt-get install -y \
+    curl \
+    procps \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN curl -fsSL https://ollama.com/install.sh | sh
+
+RUN ollama start & \
+    sleep 5 && \
+    ollama run llama3.2:1b && \
+    kill $(pgrep ollama)
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . /app
+
+EXPOSE 8000
+
+CMD ["sh", "-c", "ollama serve & uvicorn main:app --host 0.0.0.0 --port 8000 --reload"]

README.md

@@ -1,10 +1,32 @@
----
-title: Vps
-emoji: 🐨
-colorFrom: red
-colorTo: pink
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Dockerized FastAPI LLM Setup
+
+This repository contains a FastAPI application packaged inside a Docker container for easy deployment and scalability. Follow the steps below to build and run the containerized FastAPI application.
+
+## Prerequisites
+
+Ensure you have the following installed on your system before proceeding:
+
+- Docker (https://docs.docker.com/get-docker/)
+
+## Steps to Build and Run the Dockerized FastAPI Application
+
+Build the Docker Image
+Run the following command to build the Docker image from the Dockerfile in your project directory. This will create a Docker image named `my-fastapi-app`:
+
+`docker build -t my-fastapi-app .`
+
+Run the Docker Container
+Once the image is built, you can run the container and map it to port `8000` on your local machine. Use the following command:
+
+`docker run -p 8000:8000 my-fastapi-app`
+
+Explanation: - `-p 8000:8000`: Maps port 8000 on your local machine to port 8000 inside the Docker container, making the FastAPI app accessible at `http://localhost:8000`.
+
+Access the Application
+After running the container, the FastAPI app should be accessible at:
+
+`http://localhost:8000`
+
+You can interact with the API and view the automatically generated documentation provided by FastAPI at:
+
+`http://localhost:8000/docs`

main.py

@@ -0,0 +1,40 @@
+import ollama
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from typing import List
+
+app = FastAPI()
+
+# Model for the API input
+class PromptRequest(BaseModel):
+    model: str = "llama3.2:1b"
+    prompt: str
+
+# Helper function to interact with ollama
+async def generate_response(model: str, prompt: str) -> str:
+    try:
+        # Call ollama's chat function and stream the response
+        stream = ollama.chat(
+            model=model,
+            messages=[{'role': 'user', 'content': prompt}],
+            stream=True
+        )
+
+        response_text = ""
+        # Collect the streamed content
+        for chunk in stream:
+            response_text += chunk['message']['content']
+
+        return response_text
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error generating response: {e}")
+
+@app.post("/generate")
+async def generate_text(request: PromptRequest):
+    model = request.model
+    prompt = request.prompt
+
+    # Generate the response using the helper function
+    response = await generate_response(model, prompt)
+
+    return {"generated_text": response}

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+httpx
+ollama