groundx-python-sdk 1.3.18

Client for GroundX API

Groundx

Ground Your RAG Apps in Fact not Fiction

Table of Contents

• Requirements
• Installation
• Getting Started
• Async
• Reference
  • groundx.buckets.create
  • groundx.buckets.delete
  • groundx.buckets.get
  • groundx.buckets.list
  • groundx.buckets.update
  • groundx.documents.crawl_website
  • groundx.documents.delete
  • groundx.documents.delete1
  • groundx.documents.get
  • groundx.documents.get_processing_status_by_id
  • groundx.documents.list
  • groundx.documents.lookup
  • groundx.documents.upload_local
  • groundx.documents.upload_remote
  • groundx.health.get
  • groundx.health.list
  • groundx.projects.add_bucket
  • groundx.projects.create
  • groundx.projects.delete
  • groundx.projects.get
  • groundx.projects.list
  • groundx.projects.remove_bucket
  • groundx.projects.update
  • groundx.search.content

Requirements

Python >=3.7

Installation

pip install groundx-python-sdk==1.3.18

Getting Started

from pprint import pprint
from groundx import Groundx, ApiException

groundx = Groundx(
    api_key="YOUR_API_KEY",
)

try:
    # create
    create_response = groundx.buckets.create(
        name="your_bucket_name",
    )
    pprint(create_response.body)
    pprint(create_response.body["bucket"])
    pprint(create_response.headers)
    pprint(create_response.status)
    pprint(create_response.round_trip_time)
except ApiException as e:
    print("Exception when calling BucketsApi.create: %s\n" % e)
    pprint(e.body)
    pprint(e.headers)
    pprint(e.status)
    pprint(e.reason)
    pprint(e.round_trip_time)

Async

async support is available by prepending a to any method.

import asyncio
from pprint import pprint
from groundx import Groundx, ApiException

groundx = Groundx(
    api_key="YOUR_API_KEY",
)


async def main():
    try:
        # create
        create_response = await groundx.buckets.acreate(
            name="your_bucket_name",
        )
        pprint(create_response.body)
        pprint(create_response.body["bucket"])
        pprint(create_response.headers)
        pprint(create_response.status)
        pprint(create_response.round_trip_time)
    except ApiException as e:
        print("Exception when calling BucketsApi.create: %s\n" % e)
        pprint(e.body)
        pprint(e.headers)
        pprint(e.status)
        pprint(e.reason)
        pprint(e.round_trip_time)


asyncio.run(main())

Reference

groundx.buckets.create

Create a new bucket.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

create_response = groundx.buckets.create(
    name="your_bucket_name",
)

⚙️ Parameters

name: str

⚙️ Request Body

BucketCreateRequest

🔄 Return

BucketResponse

🌐 Endpoint

/v1/bucket post

🔙 Back to Table of Contents

---

groundx.buckets.delete

Delete a bucket.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

delete_response = groundx.buckets.delete(
    bucket_id=1,
)

⚙️ Parameters

bucket_id: int

The bucketId of the bucket being deleted.

🔄 Return

MessageResponse

🌐 Endpoint

/v1/bucket/{bucketId} delete

🔙 Back to Table of Contents

---

groundx.buckets.get

Look up a specific bucket by its bucketId.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

get_response = groundx.buckets.get(
    bucket_id=1,
)

⚙️ Parameters

bucket_id: int

The bucketId of the bucket to look up.

🔄 Return

BucketResponse

🌐 Endpoint

/v1/bucket/{bucketId} get

🔙 Back to Table of Contents

---

groundx.buckets.list

List all buckets within your GroundX account

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

list_response = groundx.buckets.list(
    n=1,
    next_token="string_example",
)

⚙️ Parameters

n: int

The maximum number of returned documents. Accepts 1-100 with a default of 20.

next_token: str

A token for pagination. If the number of documents for a given query is larger than n, the response will include a "nextToken" value. That token can be included in this field to retrieve the next batch of n documents.

🔄 Return

BucketListResponse

🌐 Endpoint

/v1/bucket get

🔙 Back to Table of Contents

---

groundx.buckets.update

Rename a bucket.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

update_response = groundx.buckets.update(
    new_name="your_bucket_name",
    bucket_id=1,
)

⚙️ Parameters

new_name: str

The new name of the bucket being renamed.

bucket_id: int

The bucketId of the bucket being updated.

⚙️ Request Body

BucketUpdateRequest

🔄 Return

BucketUpdateResponse

🌐 Endpoint

/v1/bucket/{bucketId} put

🔙 Back to Table of Contents

---

groundx.documents.crawl_website

Upload the content of a publicly accessible website to a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

crawl_website_response = groundx.documents.crawl_website(
    websites=[
        {
            "bucket_id": 123,
            "cap": 100,
            "depth": 3,
            "source_url": "https://my.website.com",
        }
    ],
)

⚙️ Parameters

websites: WebsiteCrawlRequestWebsites

⚙️ Request Body

WebsiteCrawlRequest

🔄 Return

IngestResponse

🌐 Endpoint

/v1/ingest/documents/website post

🔙 Back to Table of Contents

---

groundx.documents.delete

Delete multiple documents hosted on GroundX

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

delete_response = groundx.documents.delete(
    document_ids=["documentIds_example"],
)

⚙️ Parameters

document_ids: List[str]

A list of documentIds which correspond to documents uploaded to GroundX

🔄 Return

IngestResponse

🌐 Endpoint

/v1/ingest/documents delete

🔙 Back to Table of Contents

---

groundx.documents.delete1

Delete a single document hosted on GroundX

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

delete1_response = groundx.documents.delete1(
    document_id="documentId_example",
)

⚙️ Parameters

document_id: str

A documentId which correspond to a document uploaded to GroundX

🔄 Return

IngestResponse

🌐 Endpoint

/v1/ingest/document/{documentId} delete

🔙 Back to Table of Contents

---

groundx.documents.get

Look up an existing document by documentId.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

get_response = groundx.documents.get(
    document_id="documentId_example",
)

⚙️ Parameters

document_id: str

The documentId of the document for which GroundX information will be provided.

🔄 Return

DocumentResponse

🌐 Endpoint

/v1/ingest/document/{documentId} get

🔙 Back to Table of Contents

---

groundx.documents.get_processing_status_by_id

Get the current status of an upload, initiated with documents.upload_remote, documents.upload_local, or documents.crawl_website, by specifying the processId (the processId is included in the response of the documents.upload functions).

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

get_processing_status_by_id_response = groundx.documents.get_processing_status_by_id(
    process_id="processId_example",
)

⚙️ Parameters

process_id: str

the processId for the upload process being checked

🔄 Return

ProcessStatusResponse

🌐 Endpoint

/v1/ingest/{processId} get

🔙 Back to Table of Contents

---

groundx.documents.list

lookup all documents across all resources which are currently on GroundX

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

list_response = groundx.documents.list(
    n=1,
    filter="string_example",
    sort="name",
    sort_order="asc",
    status="queued",
    next_token="string_example",
)

⚙️ Parameters

n: int

The maximum number of returned documents. Accepts 1-100 with a default of 20.

filter: str

Only documents with names that contain the filter string will be returned in the results.

sort: Sort

The document attribute that will be used to sort the results.

sort_order: SortOrder

The order in which to sort the results. A value for sort must also be set.

status: ProcessingStatus

A status filter on the get documents query. If this value is set, then only documents with this status will be returned in the results.

next_token: str

A token for pagination. If the number of documents for a given query is larger than n, the response will include a "nextToken" value. That token can be included in this field to retrieve the next batch of n documents.

🔄 Return

DocumentListResponse

🌐 Endpoint

/v1/ingest/documents get

🔙 Back to Table of Contents

---

groundx.documents.lookup

lookup the document(s) associated with a processId, bucketId, or projectId.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

lookup_response = groundx.documents.lookup(
    id=1,
    n=1,
    filter="string_example",
    sort="name",
    sort_order="asc",
    status="queued",
    next_token="string_example",
)

⚙️ Parameters

id: int

a processId, bucketId, or projectId

n: int

The maximum number of returned documents. Accepts 1-100 with a default of 20.

filter: str

Only documents with names that contain the filter string will be returned in the results.

sort: Sort

The document attribute that will be used to sort the results.

sort_order: SortOrder

The order in which to sort the results. A value for sort must also be set.

status: ProcessingStatus

A status filter on the get documents query. If this value is set, then only documents with this status will be returned in the results.

next_token: str

A token for pagination. If the number of documents for a given query is larger than n, the response will include a "nextToken" value. That token can be included in this field to retrieve the next batch of n documents.

🔄 Return

DocumentLookupResponse

🌐 Endpoint

/v1/ingest/documents/{id} get

🔙 Back to Table of Contents

---

groundx.documents.upload_local

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

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

upload_local_response = groundx.documents.upload_local(
    body=[
        {
            "blob": open("/path/to/file", "rb"),
            "metadata": {
                "bucket_id": 1234,
                "file_name": "my_file.txt",
                "file_type": "txt",
            },
        }
    ],
)

⚙️ Request Body

DocumentLocalUploadRequest

🔄 Return

IngestResponse

🌐 Endpoint

/v1/ingest/documents/local post

🔙 Back to Table of Contents

---

groundx.documents.upload_remote

Upload documents hosted on public URLs to a GroundX bucket.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

upload_remote_response = groundx.documents.upload_remote(
    documents=[
        {
            "bucket_id": 1234,
            "file_name": "my_file.txt",
            "file_type": "txt",
            "source_url": "https://my.source.url.com/file.txt",
        }
    ],
)

⚙️ Parameters

documents: DocumentRemoteUploadRequestDocuments

⚙️ Request Body

DocumentRemoteUploadRequest

🔄 Return

IngestResponse

🌐 Endpoint

/v1/ingest/documents/remote post

🔙 Back to Table of Contents

---

groundx.health.get

Look up the current health status of a specific service. Statuses update every 5 minutes.

🛠️ Usage

get_response = groundx.health.get(
    service="search",
)

⚙️ Parameters

service: str

The name of the service to look up.

🔄 Return

HealthResponse

🌐 Endpoint

/v1/health/{service} get

🔙 Back to Table of Contents

---

groundx.health.list

List the current health status of all services. Statuses update every 5 minutes.

🛠️ Usage

list_response = groundx.health.list()

🔄 Return

HealthResponse

🌐 Endpoint

/v1/health get

🔙 Back to Table of Contents

---

groundx.projects.add_bucket

Add an existing bucket to an existing project. Buckets and projects can be associated many to many.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

add_bucket_response = groundx.projects.add_bucket(
    project_id=1,
    bucket_id=1,
)

⚙️ Parameters

project_id: int

The projectId of the project which the bucket will be added to.

bucket_id: int

The bucketId of the bucket being added to the project.

🔄 Return

MessageResponse

🌐 Endpoint

/v1/project/{projectId}/bucket/{bucketId} post

🔙 Back to Table of Contents

---

groundx.projects.create

create a new project, a project being a collection of buckets which can be searched.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

create_response = groundx.projects.create(
    name="your_project_name",
    bucket_name="your_new_bucket_name",
)

⚙️ Parameters

name: str

The name of the project being created.

bucket_name: str

Specify bucketName to automatically create a bucket, by the name specified, and add it to the created project.

⚙️ Request Body

ProjectCreateRequest

🔄 Return

ProjectResponse

🌐 Endpoint

/v1/project post

🔙 Back to Table of Contents

---

groundx.projects.delete

Delete a project.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

delete_response = groundx.projects.delete(
    project_id=1,
)

⚙️ Parameters

project_id: int

The projectId of the project to be deleted.

🔄 Return

MessageResponse

🌐 Endpoint

/v1/project/{projectId} delete

🔙 Back to Table of Contents

---

groundx.projects.get

look up a specific project by its projectId.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

get_response = groundx.projects.get(
    project_id=1,
)

⚙️ Parameters

project_id: int

The projectId of the project to look up.

🔄 Return

ProjectResponse

🌐 Endpoint

/v1/project/{projectId} get

🔙 Back to Table of Contents

---

groundx.projects.list

list all projects within your GroundX account.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

list_response = groundx.projects.list(
    n=1,
    next_token="string_example",
)

⚙️ Parameters

n: int

The maximum number of returned documents. Accepts 1-100 with a default of 20.

next_token: str

A token for pagination. If the number of documents for a given query is larger than n, the response will include a "nextToken" value. That token can be included in this field to retrieve the next batch of n documents.

🔄 Return

ProjectListResponse

🌐 Endpoint

/v1/project get

🔙 Back to Table of Contents

---

groundx.projects.remove_bucket

remove a bucket from a project. Buckets and projects can be associated many to many, this removes one bucket to project association without disturbing others.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

remove_bucket_response = groundx.projects.remove_bucket(
    project_id=1,
    bucket_id=1,
)

⚙️ Parameters

project_id: int

The projectId of the project which the bucket will be removed from.

bucket_id: int

The bucketId of the bucket which will be removed from the project.

🔄 Return

MessageResponse

🌐 Endpoint

/v1/project/{projectId}/bucket/{bucketId} delete

🔙 Back to Table of Contents

---

groundx.projects.update

Rename a project

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

update_response = groundx.projects.update(
    new_name="your_project_name",
    project_id=1,
)

⚙️ Parameters

new_name: str

The new name of the project being renamed.

project_id: int

The projectId of the project to update.

⚙️ Request Body

ProjectUpdateRequest

🔄 Return

ProjectResponse

🌐 Endpoint

/v1/project/{projectId} put

🔙 Back to Table of Contents

---

groundx.search.content

Search documents on GroundX for the most relevant information to a given query.

The result of this query is typically used in one of two ways; result['search']['text'] can be used to provide context to a language model, facilitating RAG, or result['search']['results'] can be used to observe chunks of text which are relevant to the query, facilitating citation.

Interact with the "Request Body" below to explore the arguments of this function. Enter your GroundX API key to send a request directly from this web page. Select your language of choice to structure a code snippet based on your specified arguments.

🛠️ Usage

content_response = groundx.search.content(
    query="my search query",
    id=1,
    n=20,
    next_token="eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9",
    verbosity=0,
)

⚙️ Parameters

query: str

The search query to be used to find relevant documentation.

id: int

The bucketId or projectId of the bucket or project being searched. The documents within the specified container will be compared to the query, and relevant information will be extracted.

n: int

The maximum number of returned documents. Accepts 1-100 with a default of 20.

next_token: str

A token for pagination. If the number of search results for a given query is larger than n, the response will include a "nextToken" value. That token can be included in this field to retrieve the next batch of n search results.

verbosity: int

The amount of data returned with each search result. 0 == no search results, only the recommended context. 1 == search results but no searchData. 2 == search results and searchData.

⚙️ Request Body

SearchRequest

🔄 Return

SearchResponse

🌐 Endpoint

/v1/search/{id} post

🔙 Back to Table of Contents

---

Author

This Python package is automatically generated by Konfig