forked from PromtEngineer/localGPT
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
3ebb88d
commit 551ca29
Showing
1 changed file
with
21 additions
and
22 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,52 +1,51 @@ | ||
# PDF Question Answering API | ||
# ASK MonkS | ||
|
||
This project provides an API for processing PDF documents and answering questions based on their content. | ||
This project provides an API for processing PDF documents and answering questions based on their content. It leverages advanced NLP techniques to extract meaningful data from documents, enabling users to interact with the information in an intuitive way. | ||
|
||
## Features | ||
|
||
- Ingest PDF documents and process them into semantic chunks. | ||
- Answer questions based on the content of the ingested documents. | ||
- Provide feedback on the answers. | ||
- Highlight text in PDFs and return the modified files. | ||
- **Document Ingestion**: Ingest PDF documents and process them into semantic chunks that can be easily analyzed. | ||
- **Question Answering**: Automatically answer questions based on the content of the ingested documents. | ||
- **Feedback Mechanism**: Users can provide feedback on the answers, which can be used to improve the system. | ||
- **PDF Highlighting**: Highlight text in PDFs based on query results and return the modified files. | ||
|
||
## Installation | ||
|
||
Follow these steps to get the environment set up: | ||
|
||
1. Clone the repository: | ||
```bash | ||
git clone https://github.com/yourusername/yourrepository.git | ||
git clone https://github.com/AshishMahendra/localGPT.git | ||
``` | ||
|
||
2. Navigate to the project directory: | ||
```bash | ||
cd yourrepository | ||
cd ask_monks | ||
``` | ||
|
||
3. Install the dependencies: | ||
3. Install the necessary dependencies: | ||
```bash | ||
pip install -r requirements.txt | ||
``` | ||
|
||
4. Download the spaCy model: | ||
```bash | ||
python -m spacy download en_core_web_trf | ||
``` | ||
|
||
## Usage | ||
|
||
1. Start the FastAPI application: | ||
To use the API, follow these steps: | ||
|
||
1. Start the FastAPI server: | ||
```bash | ||
uvicorn app:app --host 0.0.0.0 --port 8000 | ||
``` | ||
|
||
2. Use the API endpoints to process documents, ask questions, provide feedback, and highlight text in PDFs. | ||
2. Once the server is running, you can interact with the API through its endpoints. Use the provided endpoints to process documents, ask questions, provide feedback, and highlight text in PDFs. | ||
|
||
## Endpoints | ||
## API Endpoints | ||
|
||
- **POST /api/run_ingest**: Ingest and process PDF documents. | ||
- **POST /api/prompt_route**: Ask questions based on the content of the ingested documents. | ||
- **POST /api/feedback**: Provide feedback on the answers. | ||
- **POST /api/highlight_pdf**: Highlight text in PDFs and return the modified files. | ||
- **POST /api/run_ingest**: Endpoint to ingest and process PDF documents. It converts PDFs into manageable chunks and prepares them for analysis. | ||
- **POST /api/prompt_route**: Use this endpoint to ask questions regarding the ingested PDF documents. It uses the processed data to generate responses. | ||
- **POST /api/feedback**: Provide feedback on the quality of the answers received. This helps in refining the accuracy and relevance of the responses. | ||
- **POST /api/highlight_pdf**: Highlight specific text in the PDFs based on the queries and return the modified PDF files. | ||
|
||
## License | ||
|
||
This project is licensed under the MIT License. | ||
This project is available under the MIT License, allowing flexibility for both personal and commercial use. |