API Reference

Release Notes

v 0.2.3 (MAR 12, 2025)

Added

  • Function: UploadModel: Upload trained deep neural network model that needs to be embedded with Tikos Reasoning Platform. PyTorch based models are supported
  • Function: UploadModelConfig: Upload the configuration related to the uploaded deep neural network model. Will accept the model param definition in JSON format as well as the model specification in YAML format
  • Function: UploadModelCaseData: Upload of the selected knowledge Cases (feature sets), that will build the initial Sequential Collection Case base
  • Function: ProcessModel: Process the uploaded deep neural network model with Synapses Logger embedding and dynamically creating the Sequential Collection Case base
  • tikos.TikosClient.uploadEmbeddingModel: Supports upload of the deep neural network model
  • tikos.TikosClient.uploadEmbeddingConfig: Supports upload of the deep neural network model configuration files
  • tikos.TikosClient.uploadModelCaseData: Upload of the selected Knowledge Cases (feature sets), that will build the initial Sequential Collection Case base
  • tikos.TikosClient.processEmbeddedModel: Process the upload deep neural network model with Synapses Logger embedding and dynamically creating the Sequential Collection Case base

v 0.2.2 (DEC 16, 2024)

Modified

  • BuildSC: accepts the Sequential Collection config (scConfig)
  • tikos.TikosClient.createSequentialCollection: accepts the Sequential Collection config (scConfig)

v.0.2.1 (DEC 2, 2024)

Added

  • tikos.TikosClient: A generic client connector that orchestrates commonly used base functions. It has been developed to facilitate easy integration with other applications and supports multithreading
    • Function: addProcessFiles: Multithreading supported file processing function. Accepts: List of filenames and file paths as a tuple.
    • Function: addFileStreams: Multithreading supported file addition function. Accepts: List of filenames and file stream as a tuple.
    • Function: addProcessFileStreams: Multithreading supported combined file addition and processing function. Accepts: List of filenames and file stream as a tuple.
    • Function: generateGraphStructures: Multithreading supported graph structure generation function. Accepts: List of filenames as contexts.
    • Function: createGraph: Multithreading supported graph creation function. Accepts: List of filenames as context.
    • Function: getGraph: Graph structure extraction function.
    • Function: getGraphRetrieval: Graph retrieval function, Accepts: Filenames as context and query.
    • Function: createSequentialCollection: Sequential Collection creation function. Accepts: Case-Type, Data File name as context and Weight Type.
    • Function: generateReasoning: Sequential Collection reasoning function. Accepts: Case-Type, Data File name as context, problem space Case as a JSON object string, Weight Type and Reasoning Type.

v0.2.0 (NOV 14, 2024)

Added

  • GetReasoning: Generate similarity reasoning of a solution for a given Sequential Collection Case

v0.1.9 (OCT 8, 2024)

Modified

  • GetGraphStructure, GetGraphStructurePerDoc, GenerateGraph, GenerateGraphPerDoc & GenerateAutoGraph, to accept the model-id configuration.

v0.1.8 (SEP 30, 2024)

Modified

  • GenerateGraph, GenerateGraphPerDoc, GenerateAutoGraph: Accept graph generation payload configuration in JSON format: {“overrideNER”:”<True/False>”, “filter”:””}. Enables finer control over the creation of node properties.

v0.1.7 (SEP 26, 2024)

Added

  • GetCustomerGraphRetrievalWithDS: Retrieve customer-specific query with Graph relationships and nodes data sets as JSON

v0.1.6 (SEP 23, 2024)

Modified

  • GetGraphRetrieval: to accept optional file reference and base model reference.
  • GetGraphRetrievalWithDS: to accept optional file reference and base model reference.

v0.1.4 (SEP 15, 2024)

Added

  • GetGraphStructurePerDoc: Accept file names and generate NER JSON of the (submitted) file.
  • GenerateGraphPerDoc: Accept a NER JSON object and create a graph of the (submitted) file.
  • GenerateAutoGraph: Accept a list of file names, that will be used to generate the NER generation automatically and create a full graph.

v0.1.2 (AUG 13, 2024)

Added

  • BuildSC: Generate the SequentialCollection knowledge structure for the associated graph Vertices from structured data sets.
  • GetSimilarCase: Providing a Problem Space (PS) Case, the Sequential collection will conduct a basic binary (BIN, default) search or advanced binary (BINADV) search and return the most similar existing Case. This does not perform any Case adaptation.

v0.1.1 (JUL 26, 2024)

Added

  • ProcessExtractFile: Be able to extract data from a specific file and support JSON-based extraction using jq-based schemas

Modified

  • ProcessExtract: Support JSON-based extraction using jq-based schemas

v0.1.0 (JUL 22, 2024)

Added

  • Licence conditions

v0.0.9 (JUL 17, 2024)

Added

  • GetGraphRetrievalWithDS: Retrieve query response along with the Graph relationships for the requested retrieve query with Graph Node data sets as JSON

v0.0.8 (JUL 12, 2024)

Added

  • GetGraphRelationships: Retrieve query response along with the Graph relationships for the requested retrieve query.

v0.0.7 (JUL 29, 2024)

Added

  • GenerateGraph: Generate the whole graph using triples in the format
    [{"term": "Term/Node/Vertex name", "element": "Associative Term/Node/Vertex name", "relationships": "Relationship between Term/Node/Vertex names"},.....{}]
  • GetGraphStructure: Get graph Nodes and Relationships that can be further refined by the user.
  • GetGraph: Get the whole graph for an extraction request.