Ingesting Documents | Documentation

If you are using the APIs directly, choose from one of the following methods.

Ingest documents hosted on public URLs into a GroundX bucket.

Upload documents hosted on a local file system into a GroundX bucket.

If you are using one of the supported SDKs, the ingest method can be used to ingest both local and remote documents.

Document

bucketId

integerRequired

The bucketId of the bucket which this file will be ingested to.

filePath

stringRequired

The local file path or remote URL of the document being ingested by GroundX.

fileName

string

The name of the file being ingested.

fileType

enum

The type of document (one of the currently supported file types).

processLevel

enum

The amount of processing to perform on chunks (default ‘full’).

searchData

object

Custom metadata which can be used to influence GroundX’s search functionality. This data can be used to further hone GroundX search.

1	from groundx import Document, GroundX
2
3	client = GroundX(
4	api_key="YOUR_API_KEY",
5	)
6	client.ingest(
7	documents=[
8	Document(
9	bucket_id=1234,
10	file_name="my_file1.txt",
11	file_path="https://my.source.url.com/file1.txt",
12	file_type="txt",
13	),
14	Document(
15	bucket_id=1234,
16	file_name="my_file2.pdf",
17	file_path="/local/path/file2.pdf",
18	file_type="pdf",
19	search_data=dict(
20	key = "value",
21	),
22	)
23	],
24	)