Skip to content

Embbeding processing

The embeddings extraction is a tool allowing to extract embedding from "title_tokens" and "content_tokens", "ner", "svo" field of tkeir document. This tools is a rest service where the API is described in API section and the configuration file is described in Configuration section.

Embeddings API

Embeddings configuration

Example of Configuration:

relation.json
{
    "logger": {
        "logging-level": "{{ project.loglevel }}"
    },
    "embeddings": {
        "models":[{
            "language":"multi",
            "use-cuda":false,
            "batch-size":256,
            "model-path-or-name":"{{ project.path }}/resources/modeling/net"
        }],
        "network": {
            "host":"0.0.0.0",
            "port":10005,
            "associate-environment": {
                "host":"SENT_EMBEDDING_HOST",
                "port":"SENT_EMBEDDING_PORT"
            }
        },
        "runtime":{
            "request-max-size":100000000,
            "request-buffer-queue-size":100,
            "keep-alive":true,
            "keep-alive-timeout":500,
            "graceful-shutown-timeout":500.0,
            "request-timeout":600,
            "response-timeout":600,
            "workers":1
        }
    }
}

Embedding configuration is an aggreation of network configuration, serialize configuration, runtime configuration (in field converter), logger (at top level). The models fiels allows to configure model access

"language":"multi",

: "use-cuda":true, "batch-size":256

  • language :the language of model (not yet implemented, use multi for language agnostic)
  • use-cuda: use cuda to run the model
  • batch-size : size of batch sent to the model

Configure Embeddings logger

Logger is configuration at top level of json in logger field.

Example of Configuration:

logger configuration
{
    "logger": {
        "logging-level": "debug"
    }    
}

The logger fields is:

  • logging-level

It can be set to the following values:

  • debug for the debug level and developper information
  • info for the level of information
  • warning to display only warning and errors
  • error to display only error
  • critical to display only error

Configure Embeddings Network

Example of Configuration:

network configuration
{
    "network": {
        "host":"0.0.0.0",
        "port":8080,
        "associate-environment": {
            "host":"HOST_ENVNAME",
            "port":"PORT_ENVNAME"
        },
        "ssl":
        {
            "certificate":"path/to/certificate",
            "key":"path/to/key"
        }
    }
}

The network fields:

  • host : hostname

  • port : port of the service

  • associated-environement

: default one. This field is not mandatory.

  • "host" : associated "host" environment variable

  • "port" : associated "port" environment variable

  • ssl : ssl configuration IN PRODUCTION IT IS MANDATORY TO USE CERTIFICATE AND KEY THAT ARE *NOT* SELF SIGNED

  • cert : certificate file

  • key : key file

Configure Embeddings runtime

Example of Configuration:

network configuration
{
    "runtime":{
        "request-max-size":100000000,
        "request-buffer-queue-size":100,
        "keep-alive":true,
        "keep-alive-timeout":5,
        "graceful-shutown-timeout":15.0,
        "request-timeout":60,
        "response-timeout":60,
        "workers":1
    }    
}

The Runtime fields:

  • request-max-size : how big a request may be (bytes)

  • request-buffer-queue-size: request streaming buffer queue size

  • request-timeout : how long a request can take to arrive (sec)

  • response-timeout : how long a response can take to process (sec)

  • keep-alive: keep-alive

  • keep-alive-timeout: how long to hold a TCP connection open (sec)

  • graceful-shutdown_timeout : how long to wait to force close non-idle connection (sec)

  • workers : number of workers for the service on a node

  • associated-environement : if one of previous field is on the associated environment variables that allows to replace the default one. This field is not mandatory.

  • request-max-size : overwrite with environement variable

  • request-buffer-queue-size: overwrite with environement variable
  • request-timeout : overwrite with environement variable
  • response-timeout : overwrite with environement variable
  • keep-alive: overwrite with environement variable
  • keep-alive-timeout: overwrite with environement variable
  • graceful-shutdown_timeout : overwrite with environement variable
  • workers : overwrite with environement variable

Embeddings service

To run the command type simply from tkeir directory:

python3 thot/embeddings_svc.py --config=<path to embeddings configuration file>

or if you install tkeir wheel:

tkeir-embeddings-svc --config=<path to embeddings configuration file>

A light client can be run through the command

python3 thot/embeddings_client.py --config=<path to embeddings configuration file> --input=<input directory> --output=<output directory>

or if you install tkeir wheel:

tkeir-embeddings-client --config=<path to embeddings configuration file> --input=<input directory> --output=<output directory>

Embeddings Tests

The Embeddings service come with unit and functional testing.

Embeddings Unit tests

Unittest allows to test Tokenizer classes only.

python3 -m unittest thot/tests/unittests/TestEmbeddingConfiguration.py
python3 -m unittest thot/tests/unittests/TestEmbeddings.py

Embeddings Functional tests

python3 -m unittest thot/tests/functional_tests/TestEmbeddingsSvc.py