s4um1l commited on
Commit
70e8ff8
·
1 Parent(s): 9a00962

docker changes and readme file

Browse files
Files changed (2) hide show
  1. Dockerfile +4 -11
  2. README.md +50 -0
Dockerfile CHANGED
@@ -16,15 +16,8 @@ RUN uv pip install --system -r requirements.txt
16
  # Copy the application code
17
  COPY . .
18
 
19
- # Expose the port Chainlit runs on
20
- EXPOSE 8000
21
 
22
- # Command to run the application
23
- CMD ["chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "8000"]
24
-
25
- # Add this line to your Dockerfile
26
- RUN --mount=type=secret,id=openai_api_key \
27
- cat /run/secrets/openai_api_key > /app/.env
28
-
29
- ARG OPENAI_API_KEY
30
- ENV OPENAI_API_KEY=$OPENAI_API_KEY
 
16
  # Copy the application code
17
  COPY . .
18
 
19
+ # Expose the port for Hugging Face Spaces (required)
20
+ EXPOSE 7860
21
 
22
+ # Command to run the application on Hugging Face's required port
23
+ CMD ["chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]
 
 
 
 
 
 
 
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: OpenAI Chainlit Chat App
3
+ emoji: 💬
4
+ colorFrom: blue
5
+ colorTo: indigo
6
+ sdk: docker
7
+ sdk_version: "latest"
8
+ app_file: app.py
9
+ pinned: false
10
+ ---
11
+
12
+ # OpenAI Chainlit Chat App
13
+
14
+ A streamlined, production-ready chat application powered by OpenAI's GPT models and built with Chainlit. This app provides an interactive chat experience with streaming responses, similar to ChatGPT.
15
+
16
+ ## Features
17
+
18
+ - 💬 **Real-time streaming responses** - See AI replies as they're being generated
19
+ - 🧠 **Full conversation memory** - AI maintains context throughout the chat
20
+ - 🔄 **Async processing** for optimal performance
21
+ - 🛠️ **Error handling** for robust operation
22
+
23
+ ## Technical Details
24
+
25
+ This application is built with:
26
+ - **Chainlit** - Provides the modern chat interface
27
+ - **OpenAI API** - Powers the AI responses using GPT models
28
+ - **Docker** - Containerizes the application for easy deployment
29
+ - **UV** - Efficient Python package management
30
+
31
+ ## Local Development
32
+
33
+ To run this application locally:
34
+
35
+ 1. Clone the repository:
36
+ 2. Create a `.env` file with your OpenAI API key:
37
+
38
+ 3. Build and run with Docker:
39
+
40
+ 4. Access the application at http://localhost:7860
41
+
42
+ ## Deployment
43
+
44
+ This app is configured for easy deployment on Hugging Face Spaces. The Docker container automatically runs on port 7860 as required by Hugging Face.
45
+
46
+ Remember to add your OpenAI API key as a secret in the Hugging Face Space settings.
47
+
48
+ ## License
49
+
50
+ MIT