README

Knowledge API

The Knowledge Base feature visualises the various aspects of the RAG pipeline and provides an easy-to-use user interface for application builders to manage their personal or team knowledge base and quickly integrate it into AI applications.

Compared to the static pre-training data built into AI models, the content in the knowledge base can be updated in real-time, ensuring that LLMs have access to the latest information and avoiding problems caused by outdated or missing information.

Upon receiving a user's question, the LLM will first retrieve content within the knowledge base based on keywords. Based on the keywords, the knowledge base will recall blocks of content with high relevance rankings and provide key context to the LLM to assist it in generating more accurate answers.

In this way, developers can ensure that the LLM does not only rely on knowledge from the training data, but is also able to process dynamic data from real-time documents and databases, thus increasing the accuracy and relevance of the answers.

Base URL

https://api-platform.digitpulse.ai/v1

Authentication

The Service API uses API-Key authentication. Strongly recommend storing your API Key on the server-side, not shared or stored on the client-side, to avoid possible API-Key leakage that can lead to serious consequences.

For all API requests, include your API Key in the AuthorizationHTTP Header, as shown below:

Authorization: Bearer {API_KEY}

Error Code

code	status	message
no_file_uploaded	400	Please upload your file.
too_many_files	400	Only one file is allowed.
file_too_large	413	File size exceeded.
unsupported_file_type	415	File type not allowed.
high_quality_dataset_only	400	Current operation only supports 'high-quality' datasets.
dataset_not_initialized	400	The dataset is still being initialized or indexing. Please wait a moment.
archived_document_immutable	403	The archived document is not editable.
dataset_name_duplicate	409	The dataset name already exists. Please modify your dataset name.
invalid_action	400	Invalid action.
document_already_finished	400	The document has been processed. Please refresh the page or go to the document details.
document_indexing	400	The document is being processed and cannot be edited.
invalid_metadata	400	The metadata content is incorrect. Please check and verify.

Example

  {
    "code": "no_file_uploaded",
    "message": "Please upload your file.",
    "status": 400
  }

Knowledge API#

Base URL#

Authentication#

Error Code#

Example#

Knowledge API

Base URL

Authentication

Error Code

Example