Pull Request - File Loaders Extension for Quizzify
Summary
Added loaders for the following file types:
CSV
DOCX
PPTX
Youtube
WebPage
TXT
PDF
Added filtering as well. For example for csv, user can mention startRow and endRow and specific columns and based on that content, quiz questions would be generated.
Changes
Added above listed file loaders and thoroughly tested it.
Created a file called as loaders.py and added all the loaders in it.
Refactored URL Loader a bit and tweaked some parameters of RAG pipeline and added schemas for each file type in tool_registry to support filtering.
Made filetype parameter as mandatory and it needs to be passed in request body along with url mandatory field.
Testing
Each loader was tested using Adhoc Testing.
Results
All six loaders are working perfectly fine with and without filtering criteria.
Notes
This feature extends the support for other loaders as well apart from pdf files which enhances file type support.
Screenshots
YouTube Sample Request and Response
Webpage Sample Request and Response
TXT Sample Request and Response
DOCX Sample Request and Response
PPTX Sample Request and Response
CSV Sample Request and Response
PDF Sample Request and Response
How to Test
Clone the repo in your local
Create and activate virtual environment
Use pip install -r requirements.txt to install required libraries.
Create .env file with ENV_TYPE, GCP_PROJECT_ID and GOOGLE_API_KEY fields. Env type is dev, gcp_project_id is your project id from cloud console project, google_api_key is your api key from AI studio.
Then type ./local-start.sh to start the application.
Add sample requests and responses for each file type as mentioned above in screenshots and test it.
Pull Request - File Loaders Extension for Quizzify
Summary
Added loaders for the following file types:
Added filtering as well. For example for csv, user can mention startRow and endRow and specific columns and based on that content, quiz questions would be generated.
Changes
Testing
Each loader was tested using Adhoc Testing.
Results
All six loaders are working perfectly fine with and without filtering criteria.
Notes
Screenshots
YouTube Sample Request and Response
Webpage Sample Request and Response
TXT Sample Request and Response
DOCX Sample Request and Response
PPTX Sample Request and Response
CSV Sample Request and Response
PDF Sample Request and Response
How to Test
Clone the repo in your local
Create and activate virtual environment
Use pip install -r requirements.txt to install required libraries.
Create .env file with ENV_TYPE, GCP_PROJECT_ID and GOOGLE_API_KEY fields. Env type is dev, gcp_project_id is your project id from cloud console project, google_api_key is your api key from AI studio.
Then type ./local-start.sh to start the application.
Add sample requests and responses for each file type as mentioned above in screenshots and test it.