Skip to content

mionaD-upc/IntentDetect-TFM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

IntentDetect

Capturing Analytical Intents from Text

Getting started

Before you begin

  • You should have Docker installed on your machine.

  • You should have .env file in the root folder with your API keys stored.

    OPENAI_API_KEY=<YOUR OPENAI_API_KEY>
    LlamaAPI_KEY=<LlamaAPI_KEY>
    

For more information on how to obtain API Keys, refer to : OpenAI and LLama AI.

Building Docker image

In order to build a Docker image yourself run the following command.

# run build Docker command
docker build . -t <image-name>:<image-tag>

Based on your platform installation you may need to use sudo or other platform specific adjustments.

Make sure that you do not have put any private data in the current folder as it will be added to the Docker image you created and as such available to anyone who come in position of the image.

Start Docker container

For starting Docker container we can use the docker commands.

# run container
docker run --rm -p 9000:9000 --name='<container-name>' <image-name>:<image-tag>

Usage Example

# build docker image
docker build -t intent-detect:latest .
# run container
docker run --rm -p 9000:9000 --name='intent-detect-c1' intent-detect:latest

Optionally, you can run the container such that your local host is mounted to the Docker container to keep track of input and output files. This way, all input data and results are saved to your local host upon container termination.

# run container (local host is mounted to the Docker container)
docker run --rm -p 9000:9000 -v $PWD/src/results:/src/results -v $PWD/src/uploads:/src/uploads --name='intent-detect-c1' intent-detect:latest

If needed you can connect to running Docker container.

# connect to started container
docker exec -it intent-detect-c1 /bin/sh

Navigate to application

In order to engage with application you should navigate your web browser to http://localhost:9000 or you can use curl.

curl -X GET http://localhost:9000

References

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published