Sign in
Context Chunks

Chunks Retrieval

Given a text, returns the most relevant chunks from the ingested documents.

The returned information can be used to generate prompts that can be passed to /completions or /chat/completions APIs. Note: it is usually a very fast API, because only the Embeddings model is involved, not the LLM. The returned information contains the relevant chunk text together with the source document it is coming from. It also contains a score that can be used to compare different results.

The max number of chunks to be returned is set using the limit param.

Previous and next chunks (pieces of text that appear right before or after in the document) can be fetched by using the prev_next_chunks field.

The documents being used can be filtered using the context_filter and passing the document IDs to be used. Ingested documents IDs can be found using /ingest/list endpoint. If you want all ingested documents to be used, remove context_filter altogether.

post/v1/chunks

Request body

textstring required
limitinteger
prev_next_chunksinteger

Example request

{
  "text": "Q3 2023 sales",
  "context_filter": {
    "docs_ids": [
      "c202d5e6-7b69-4869-81cc-dd574ee8ee11"
    ]
  },
  "prev_next_chunks": 2
}

Response

Successful Response

object'list' required
model'private-gpt' required

Example response

{
  "data": [
    {
      "score": 0.023,
      "document": {
        "doc_id": "c202d5e6-7b69-4869-81cc-dd574ee8ee11",
        "doc_metadata": {
          "file_name": "Sales Report Q3 2023.pdf",
          "page_label": "2"
        }
      },
      "text": "Outbound sales increased 20%, driven by new leads.",
      "previous_texts": [
        "SALES REPORT 2023",
        "Inbound didn't show major changes."
      ],
      "next_texts": [
        "New leads came from Google Ads campaign.",
        "The campaign was run by the Marketing Department"
      ]
    }
  ]
}

Changes