Spaces:
Sleeping
Sleeping
Update README
Browse files
README.md
CHANGED
@@ -2,9 +2,7 @@
|
|
2 |
|
3 |
A Simple LLM app that demonstrates a Retrieval-Augmented Generation (RAG) model for question-answering using LangChain, ChromaDB, and OpenAI's language models.
|
4 |
|
5 |
-
The app allows users to upload documents (PDFs or text files), and then ask questions related to the content of those documents.
|
6 |
-
|
7 |
-
The RAG model retrieves relevant passages from the documents and generates an answer based on the retrieved context.
|
8 |
|
9 |
---
|
10 |
|
@@ -12,21 +10,46 @@ The RAG model retrieves relevant passages from the documents and generates an an
|
|
12 |
|
13 |
---
|
14 |
|
15 |
-
##
|
16 |
|
17 |
-
-
|
18 |
-
-
|
19 |
-
-
|
20 |
-
-
|
|
|
|
|
|
|
21 |
|
22 |
-
|
23 |
|
24 |
-
Clone the repository:
|
25 |
|
26 |
-
```
|
27 |
git clone https://github.com/vinhnx/InkChatGPT.git
|
28 |
```
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
1. **Open VSCode and Create a New Python Environment**:
|
31 |
|
32 |
- Open Visual Studio Code.
|
@@ -44,30 +67,22 @@ git clone https://github.com/vinhnx/InkChatGPT.git
|
|
44 |
|
45 |
- From the File menu, choose "Open Folder" or "Open..." and navigate to the project folder containing the `app.py` file.
|
46 |
|
47 |
-
4. **
|
48 |
-
|
49 |
-
- Open a new Terminal in VSCode by clicking "Terminal" > "New Terminal" or pressing `Ctrl+Shift+`" (Windows/Linux) or `Cmd+Shift+`" (macOS).
|
50 |
-
- In the terminal, run the following command to install the required packages:
|
51 |
-
```
|
52 |
-
pip install streamlit langchain chromadb openai tiktoken pypdf
|
53 |
-
```
|
54 |
-
|
55 |
-
5. **Configure the App**:
|
56 |
|
57 |
- Open the `app.py` file in the VSCode editor.
|
58 |
- Set your OpenAI API key by modifying the `OPENAI_API_KEY` variable.
|
59 |
- Optionally, you can change the `CHROMA_PERSIST_DIRECTORY` and `OPENAI_MODEL` variables according to your preferences.
|
60 |
|
61 |
-
|
62 |
|
63 |
- In the terminal, navigate to the project directory if you're not already there.
|
64 |
- Run the following command to start the Streamlit app:
|
65 |
-
```
|
66 |
streamlit run app.py
|
67 |
```
|
68 |
- This will start the Streamlit app and provide you with a local URL to access the app in your web browser.
|
69 |
|
70 |
-
|
71 |
|
72 |
- Open the provided local URL in your web browser.
|
73 |
- You should see the InkChatGPT interface.
|
@@ -75,18 +90,18 @@ git clone https://github.com/vinhnx/InkChatGPT.git
|
|
75 |
|
76 |
## Contributing
|
77 |
|
78 |
-
Contributions are welcome! If you'd like to improve the
|
79 |
|
80 |
1. Fork the repository
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
|
86 |
## License
|
87 |
|
88 |
-
This project is licensed under the MIT License.
|
89 |
|
90 |
## Contact
|
91 |
|
92 |
-
I'm Vinh, [@vinhnx](https://x.com/vinhnx) on almost everywhere.
|
|
|
2 |
|
3 |
A Simple LLM app that demonstrates a Retrieval-Augmented Generation (RAG) model for question-answering using LangChain, ChromaDB, and OpenAI's language models.
|
4 |
|
5 |
+
The app allows users to upload documents (PDFs or text files), and then ask questions related to the content of those documents. The RAG model retrieves relevant passages from the documents and generates an answer based on the retrieved context.
|
|
|
|
|
6 |
|
7 |
---
|
8 |
|
|
|
10 |
|
11 |
---
|
12 |
|
13 |
+
## Features
|
14 |
|
15 |
+
- **Document Upload**: Supports uploading PDF and text files.
|
16 |
+
- **Question Answering**: Ask questions related to the uploaded documents.
|
17 |
+
- **Retrieval-Augmented Generation (RAG)**: Utilizes a RAG model for context-aware question answering.
|
18 |
+
- **LangChain Integration**: Leverages LangChain for building the RAG model.
|
19 |
+
- **ChromaDB**: Efficient vector storage and retrieval using ChromaDB.
|
20 |
+
- **OpenAI Language Models**: Powered by OpenAI's language models for answer generation.
|
21 |
+
- **Streamlit UI**: Interactive and user-friendly web interface.
|
22 |
|
23 |
+
## Installation
|
24 |
|
25 |
+
1. Clone the repository:
|
26 |
|
27 |
+
```shellscript
|
28 |
git clone https://github.com/vinhnx/InkChatGPT.git
|
29 |
```
|
30 |
|
31 |
+
2. Navigate to the project directory:
|
32 |
+
|
33 |
+
```shellscript
|
34 |
+
cd InkChatGPT
|
35 |
+
```
|
36 |
+
|
37 |
+
3. Create a new Python environment and activate it (e.g., using `venv` or `conda`).
|
38 |
+
|
39 |
+
4. Install the required packages:
|
40 |
+
|
41 |
+
```shellscript
|
42 |
+
pip install streamlit langchain chromadb openai tiktoken pypdf
|
43 |
+
```
|
44 |
+
|
45 |
+
or, run
|
46 |
+
|
47 |
+
```shellscript
|
48 |
+
pip install -r requirements.txt
|
49 |
+
```
|
50 |
+
|
51 |
+
## Usage
|
52 |
+
|
53 |
1. **Open VSCode and Create a New Python Environment**:
|
54 |
|
55 |
- Open Visual Studio Code.
|
|
|
67 |
|
68 |
- From the File menu, choose "Open Folder" or "Open..." and navigate to the project folder containing the `app.py` file.
|
69 |
|
70 |
+
4. **Configure the App**:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
- Open the `app.py` file in the VSCode editor.
|
73 |
- Set your OpenAI API key by modifying the `OPENAI_API_KEY` variable.
|
74 |
- Optionally, you can change the `CHROMA_PERSIST_DIRECTORY` and `OPENAI_MODEL` variables according to your preferences.
|
75 |
|
76 |
+
5. **Run the Streamlit App**:
|
77 |
|
78 |
- In the terminal, navigate to the project directory if you're not already there.
|
79 |
- Run the following command to start the Streamlit app:
|
80 |
+
```shellscript
|
81 |
streamlit run app.py
|
82 |
```
|
83 |
- This will start the Streamlit app and provide you with a local URL to access the app in your web browser.
|
84 |
|
85 |
+
6. **Use the App**:
|
86 |
|
87 |
- Open the provided local URL in your web browser.
|
88 |
- You should see the InkChatGPT interface.
|
|
|
90 |
|
91 |
## Contributing
|
92 |
|
93 |
+
Contributions are welcome! If you'd like to improve the InkChatGPT, please follow these steps:
|
94 |
|
95 |
1. Fork the repository
|
96 |
+
2. Create a new branch: `git checkout -b feature/my-feature`
|
97 |
+
3. Commit your changes: `git commit -am 'Add some feature'`
|
98 |
+
4. Push to the branch: `git push origin feature/my-feature`
|
99 |
+
5. Create a new Pull Request
|
100 |
|
101 |
## License
|
102 |
|
103 |
+
This project is licensed under the [MIT License](LICENSE).
|
104 |
|
105 |
## Contact
|
106 |
|
107 |
+
I'm Vinh, [@vinhnx](https://x.com/vinhnx) on almost everywhere. Feel free to reach out with any questions or feedback!
|