Chunks Retrieval | PrivateGPT

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.

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.

Request

This endpoint expects an object.

textstringRequired

context_filterobjectOptional

limitintegerOptionalDefaults to 10

prev_next_chunksintegerOptionalDefaults to 0

Response

This endpoint returns an object.

object"list"

model"private-gpt"

datalist of objects

Errors

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

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.

1	import requests
2
3	url = "https://host.com/v1/chunks"
4
5	payload = { "text": "text" }
6	headers = {"Content-Type": "application/json"}
7
8	response = requests.post(url, json=payload, headers=headers)
9
10	print(response.json())

1	{
2	"object": "list",
3	"model": "private-gpt",
4	"data": [
5	{
6	"object": "context.chunk",
7	"score": 1.1,
8	"document": {
9	"object": "ingest.document",
10	"doc_id": "doc_id"
11	},
12	"text": "text",
13	"previous_texts": [
14	"previous_texts"
15	],
16	"next_texts": [
17	"next_texts"
18	]
19	}
20	]
21	}