numind 0.2.2__tar.gz → 0.3.1__tar.gz

{numind-0.2.2 → numind-0.3.1}/.github/workflows/lint.yml

@@ -10,7 +10,7 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - uses: astral-sh/ruff-action@v3
         with:
           args: "--version"  # added to not run the check command as done by default

{numind-0.2.2 → numind-0.3.1}/.github/workflows/publish-pypi.yml

@@ -17,9 +17,9 @@ jobs:
     name: Build distribution
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v7
         with:
           python-version: "3.x"
       - name: Install hatch

{numind-0.2.2 → numind-0.3.1}/.github/workflows/sdk-auto-update.yml

@@ -22,7 +22,7 @@ jobs:
     steps:
       # Step 1: Check out the repository's code
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       # Step 2: Fetch the latest buildVersion from the API
       - name: Fetch latest API version
@@ -68,7 +68,7 @@ jobs:
       # Step 5: Setup Python
       - name: Set up Python
         if: steps.check_pr.outputs.pr_exists == 'false'
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v7
         with:
           python-version: "3.x"
 
@@ -83,7 +83,7 @@ jobs:
         run: |
           set -e # Exit immediately if a command exits with a non-zero status.
           echo "Generating new SDK for version ${{ steps.fetch_version.outputs.version }}..."
-          sh sdk_generation/gen_sdk.sh
+          bash sdk_generation/gen_sdk.sh
 
       # Step 8: Create a Pull Request if there are any changes
       - name: Create Pull Request

{numind-0.2.2 → numind-0.3.1}/.github/workflows/tests.yml

@@ -17,7 +17,7 @@ jobs:
         os: [ ubuntu-latest, macos-latest, windows-latest ]
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
 
       - name: Install uv
         uses: astral-sh/setup-uv@v7

{numind-0.2.2 → numind-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: numind
-Version: 0.2.2
+Version: 0.3.1
 Summary: SDK to interact with the NuMind models API.
 Project-URL: Homepage, https://github.com/numindai/nuextract-platform-sdk
 Project-URL: Repository, https://github.com/numindai/nuextract-platform-sdk.git
@@ -45,6 +45,8 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9
 Requires-Dist: aiohttp-retry>=2.8.3
 Requires-Dist: aiohttp>=3.8.4
+Requires-Dist: jsonschema
+Requires-Dist: orjson
 Requires-Dist: pydantic>=2.11
 Requires-Dist: python-dateutil>=2.8.2
 Requires-Dist: typing-extensions>=4.7.1
@@ -99,6 +101,7 @@ from numind import NuMindAsync
 client = NuMindAsync(api_key="API_KEY")
 requests = [{}]
 
+
 async def main():
     return [
         await client.extract_structured_data(project_id, **request_kwargs)
@@ -120,14 +123,14 @@ template = {
     "destination": {
         "name": "verbatim-string",
         "zip_code": "string",
-        "country": "string"
+        "country": "string",
     },
     "accommodation": "verbatim-string",
     "activities": ["verbatim-string"],
     "duration": {
         "time_unit": ["day", "week", "month", "year"],
-        "time_quantity": "integer"
-    }
+        "time_quantity": "integer",
+    },
 }
 input_text = """My dream vacation would be a month-long escape to the stunning islands of Tahiti.
 I’d stay in an overwater bungalow in Bora Bora, waking up to crystal-clear turquoise waters and breathtaking sunrises.
@@ -166,7 +169,7 @@ print(output)
 
 ### Create a good template
 
-NuExtract uses JSON schemas as extraction templates which specify the information to retrieve and their types, which are:
+NuExtract uses JSON extraction templates which specify the information to retrieve and their types, which are:
 
 * **string**: a text, whose value can be abstract, i.e. totally free and can be deduced from calculations, reasoning, external knowledge;
 * **verbatim-string**: a purely extractive text whose value must be present in the document. Some flexibility might be allowed on the formatting, e.g. new lines and escaped characters (e.g. `\n`) in a documents might be represented with a space;
@@ -182,7 +185,33 @@ Additionally, the value of a field can be:
 * an **enum**, i.e. a list of elements to choose from of the form `["choice1", "choice2", ...]`. For values of this type, just set the value of the item to choose, e.g. "choice1", and do not set the value as an array containing the item such as `["choice1"]`;
 * a **multi-enum**, i.e. a list from which multiple elements can be picked, of the form `[["choice1", "choice2", ...]]` (double square brackets).
 
-#### Inferring a template
+### Converting JSON schema / Pydantic models to NuExtract template
+
+The SDK offers a method to convert JSON schemas to NuExtract templates:
+
+```Python
+from typing import Literal
+
+from pydantic import Field, BaseModel
+from numind.nuextract_utils import convert_json_schema_to_nuextract_template
+
+
+class HotelBooking(BaseModel):
+    city: str
+    check_in_date: str = Field(description="date")
+    check_out_date: str = Field(description="date")
+    number_of_guests: int
+    room_type: Literal["single", "double", "suite"]
+
+
+template, dropped_branches, descriptions = convert_json_schema_to_nuextract_template(
+    HotelBooking.model_json_schema()
+)
+
+# {'check_in_date': 'date', 'check_out_date': 'date', 'city': 'string', 'number_of_guests': 'integer', 'room_type': ['single', 'double', 'suite']}
+```
+
+### Inferring a template
 
 The "infer_template" method allows to quickly create a template that you can start to work with from a text description.
 
@@ -270,41 +299,52 @@ markdown = client.extract_content(input_file)
 
 ### Extracting Information from Documents
 
-Once your project is ready, you can use it to extract information from documents in real time via this RESTful API.
-
-Each project has its own extraction endpoint:
+Once your structured extraction project is ready, submit a document to the endpoint:
 
-`https://nuextract.ai/api/projects/{projectId}/extract`
+`https://nuextract.ai/api/structured-extraction/{structuredProjectId}/jobs`
 
-You provide it a document and it returns the extracted information according to the task defined in the project. To use it, you need:
+To use it, you need:
 
 - To create an API key in the [Account section](https://nuextract.ai/app/user?content=api)
-- To replace `{projectId}` by the project ID found in the API tab of the project
+- To replace `{structuredProjectId}` by the project ID found in the API tab of the structured extraction project
 
-You can test your extraction endpoint in your terminal using this command-line example with curl (make sure that you replace values of `PROJECT_ID` and `NUEXTRACT_API_KEY`):
+This endpoint creates an asynchronous extraction job. Use the returned `jobId` to retrieve the result from:
+
+`https://nuextract.ai/api/structured-extraction/jobs/{structuredExtractionJobId}`
+
+You can test your extraction endpoint in your terminal using this command-line example with curl (make sure that you replace values of `STRUCTURED_PROJECT_ID` and `NUEXTRACT_API_KEY`):
 
 ```bash
 NUEXTRACT_API_KEY=\"_your_api_key_here_\"; \\
-PROJECT_ID=\"a24fd84a-44ab-4fd4-95a9-bebd46e4768b\"; \\
-curl \"https://nuextract.ai/api/projects/${PROJECT_ID}/extract\" \\
+STRUCTURED_PROJECT_ID=\"a24fd84a-44ab-4fd4-95a9-bebd46e4768b\"; \\
+JOB_ID=$(curl \"https://nuextract.ai/api/structured-extraction/${STRUCTURED_PROJECT_ID}/jobs\" \\
   -X POST \\
   -H \"Authorization: Bearer ${NUEXTRACT_API_KEY}\" \\
-  -H \"Content-Type: application/octet-stream\" \\
-  --data-binary @\"${FILE_NAME}\"
+  -F \"file=@${FILE_NAME}\" | jq -r '.jobId')
+
+curl \"https://nuextract.ai/api/structured-extraction/jobs/${JOB_ID}\" \\
+  -H \"Authorization: Bearer ${NUEXTRACT_API_KEY}\"
 ```
 
 You can also use the [Python SDK](https://github.com/numindai/nuextract-platform-sdk#documentation), by replacing the
-`project_id`, `api_key` and `file_path` variables in the following code:
+`project_id`, `api_key` and request values in the following code:
 
 ```python
-from numind import NuMind
-from pathlib import Path
+import asyncio
+from numind import NuMindAsync
 
-client = NuMind(api_key=api_key)
-file_path = Path(\"path\", \"to\", \"document.odt\")
-with file_path.open(\"rb\") as file:
-    input_file = file.read()
-output_schema = client.post_api_projects_projectid_extract(project_id, input_file)
+client = NuMindAsync(api_key=api_key)
+requests = [{}]
+
+
+async def main():
+    return [
+        await client.extract_structured_data(project_id, **request_kwargs)
+        for request_kwargs in requests
+    ]
+
+
+responses = asyncio.run(main())
 ```
 
 ### Using the Platform via API
@@ -315,26 +355,38 @@ Everything you can do on the web platform can be done via API -
 
 #### Main resources
 
-- **Project** - user project, identified by `projectId`
+- **Structured Extraction Project** - user project for structured extraction, identified by `structuredProjectId`
+- **Content Extraction Project** - user project for content extraction, identified by `contentProjectId`
 - **File** - uploaded file,  identified by `fileId`, stored up to two weeks if not tied to an **Example**
-- **Document** - internal representation of a document, identified by `documentId`, created from a File or a text, stored up to two weeks if not tied to an Example
-- **Example** - document-extraction pair given to teach NuExtract, identified by `exampleId`, created from a Document
+- **Document** - internal representation of a document, identified by `documentId`, created from a File, stored up to two weeks if not tied to an Example
+- **Example** - document-extraction pair given to teach NuExtract, identified by `structuredExampleId`, created from a Document
+- **Job** - asynchronous extraction task, identified by `structuredExtractionJobId`
 
 #### Most common API operations
 
-- Creating a **Project** via `POST /api/projects`
-- Changing the template of a **Project** via `PATCH /api/projects/{projectId}`
+##### Structured extraction
+
+- Creating a **Structured Extraction Project** via `POST /api/structured-extraction`
+- Changing the template of a **Structured Extraction Project** via `PATCH /api/structured-extraction/{structuredProjectId}`
+- Changing settings of a **Structured Extraction Project** via `PATCH /api/structured-extraction/{structuredProjectId}/settings`
+- Uploading a file to a **File** via `POST /api/files` (up to 2 weeks storage)
+- Starting a structured extraction **Job** via `POST /api/structured-extraction/{structuredProjectId}/jobs`
+- Reading a structured extraction **Job** result via `GET /api/structured-extraction/jobs/{structuredExtractionJobId}`
+- Adding an **Example** to a **Structured Extraction Project** via `POST /api/structured-extraction/{structuredProjectId}/examples`
+
+##### Content extraction
+
+- Creating a **Content Extraction Project** via `POST /api/content-extraction`
+- Changing settings of a **Content Extraction Project** via `PATCH /api/content-extraction/{contentProjectId}/settings`
 - Uploading a file to a **File** via `POST /api/files` (up to 2 weeks storage)
-- Creating a **Document** via `POST /api/documents/text` and `POST /api/files/{fileID}/convert-to-document` from a text or a **File**
-- Adding an **Example** to a **Project** via `POST /api/projects/{projectId}/examples`
-- Changing Project settings via `POST /api/projects/{projectId}/settings`
-- Locking a **Project** via `POST /api/projects/{projectId}/lock`
+- Starting a content extraction **Job** via `POST /api/content-extraction/jobs`
+- Reading a content extraction **Job** result via `GET /api/content-extraction/jobs/{contentExtractionJobId}`
 
 This Python package is automatically generated by the [OpenAPI Generator](https://openapi-generator.tech) project:
 
 - API version: 
 - Package version: 1.0.0
-- Generator version: 7.21.0
+- Generator version: 7.22.0
 - Build package: org.openapitools.codegen.languages.PythonClientCodegen
 
 ### Documentation for API Endpoints
@@ -345,6 +397,7 @@ Class | Method | HTTP request | Description
 ------------ | ------------- | ------------- | -------------
 *ContentExtractionApi* | [**get_api_content_extraction_jobs_contentextractionjobid**](docs/ContentExtractionApi.md#get_api_content_extraction_jobs_contentextractionjobid) | **GET** /api/content-extraction/jobs/{contentExtractionJobId} | 
 *ContentExtractionApi* | [**post_api_content_extraction_jobs**](docs/ContentExtractionApi.md#post_api_content_extraction_jobs) | **POST** /api/content-extraction/jobs | 
+*ContentExtractionProjectManagementApi* | [**delete_api_content_extraction_contentprojectid**](docs/ContentExtractionProjectManagementApi.md#delete_api_content_extraction_contentprojectid) | **DELETE** /api/content-extraction/{contentProjectId} | 
 *ContentExtractionProjectManagementApi* | [**get_api_content_extraction**](docs/ContentExtractionProjectManagementApi.md#get_api_content_extraction) | **GET** /api/content-extraction | 
 *ContentExtractionProjectManagementApi* | [**patch_api_content_extraction_contentprojectid**](docs/ContentExtractionProjectManagementApi.md#patch_api_content_extraction_contentprojectid) | **PATCH** /api/content-extraction/{contentProjectId} | 
 *ContentExtractionProjectManagementApi* | [**patch_api_content_extraction_contentprojectid_settings**](docs/ContentExtractionProjectManagementApi.md#patch_api_content_extraction_contentprojectid_settings) | **PATCH** /api/content-extraction/{contentProjectId}/settings | 
@@ -356,7 +409,7 @@ Class | Method | HTTP request | Description
 *DefaultApi* | [**get_api_ping**](docs/DefaultApi.md#get_api_ping) | **GET** /api/ping | 
 *DefaultApi* | [**get_api_version**](docs/DefaultApi.md#get_api_version) | **GET** /api/version | 
 *DocumentsApi* | [**get_api_documents_documentid**](docs/DocumentsApi.md#get_api_documents_documentid) | **GET** /api/documents/{documentId} | 
-*DocumentsApi* | [**get_api_documents_documentid_content**](docs/DocumentsApi.md#get_api_documents_documentid_content) | **GET** /api/documents/{documentId}/content | 
+*DocumentsApi* | [**get_api_documents_documentid_parts_partindex_image**](docs/DocumentsApi.md#get_api_documents_documentid_parts_partindex_image) | **GET** /api/documents/{documentId}/parts/{partIndex}/image | 
 *DocumentsApi* | [**post_api_documents_documentid_new_owner**](docs/DocumentsApi.md#post_api_documents_documentid_new_owner) | **POST** /api/documents/{documentId}/new-owner | 
 *DocumentsApi* | [**post_api_documents_text**](docs/DocumentsApi.md#post_api_documents_text) | **POST** /api/documents/text | 
 *FilesApi* | [**get_api_files_fileid**](docs/FilesApi.md#get_api_files_fileid) | **GET** /api/files/{fileId} | 
@@ -371,6 +424,9 @@ Class | Method | HTTP request | Description
 *JobsApi* | [**get_api_jobs**](docs/JobsApi.md#get_api_jobs) | **GET** /api/jobs | 
 *JobsApi* | [**get_api_jobs_jobid_status**](docs/JobsApi.md#get_api_jobs_jobid_status) | **GET** /api/jobs/{jobId}/status | 
 *JobsApi* | [**get_api_jobs_jobid_stream**](docs/JobsApi.md#get_api_jobs_jobid_stream) | **GET** /api/jobs/{jobId}/stream | 
+*JobsApi* | [**post_api_jobs_jobid_cancel**](docs/JobsApi.md#post_api_jobs_jobid_cancel) | **POST** /api/jobs/{jobId}/cancel | 
+*ProjectImportExportApi* | [**get_api_extraction_projectkind_projectid_export**](docs/ProjectImportExportApi.md#get_api_extraction_projectkind_projectid_export) | **GET** /api/extraction/{projectKind}/{projectId}/export | 
+*ProjectImportExportApi* | [**post_api_extraction_import**](docs/ProjectImportExportApi.md#post_api_extraction_import) | **POST** /api/extraction/import | 
 *StructuredDataExtractionApi* | [**get_api_structured_extraction_jobs_structuredextractionjobid**](docs/StructuredDataExtractionApi.md#get_api_structured_extraction_jobs_structuredextractionjobid) | **GET** /api/structured-extraction/jobs/{structuredExtractionJobId} | 
 *StructuredDataExtractionApi* | [**post_api_structured_extraction_structuredprojectid_jobs**](docs/StructuredDataExtractionApi.md#post_api_structured_extraction_structuredprojectid_jobs) | **POST** /api/structured-extraction/{structuredProjectId}/jobs | 
 *StructuredExtractionExamplesApi* | [**delete_api_structured_extraction_structuredprojectid_examples_structuredexampleid**](docs/StructuredExtractionExamplesApi.md#delete_api_structured_extraction_structuredprojectid_examples_structuredexampleid) | **DELETE** /api/structured-extraction/{structuredProjectId}/examples/{structuredExampleId} | 
@@ -381,6 +437,7 @@ Class | Method | HTTP request | Description
 *StructuredExtractionProjectManagementApi* | [**delete_api_structured_extraction_structuredprojectid**](docs/StructuredExtractionProjectManagementApi.md#delete_api_structured_extraction_structuredprojectid) | **DELETE** /api/structured-extraction/{structuredProjectId} | 
 *StructuredExtractionProjectManagementApi* | [**get_api_structured_extraction**](docs/StructuredExtractionProjectManagementApi.md#get_api_structured_extraction) | **GET** /api/structured-extraction | 
 *StructuredExtractionProjectManagementApi* | [**get_api_structured_extraction_structuredprojectid**](docs/StructuredExtractionProjectManagementApi.md#get_api_structured_extraction_structuredprojectid) | **GET** /api/structured-extraction/{structuredProjectId} | 
+*StructuredExtractionProjectManagementApi* | [**get_api_structured_extraction_structuredprojectid_thumbnail**](docs/StructuredExtractionProjectManagementApi.md#get_api_structured_extraction_structuredprojectid_thumbnail) | **GET** /api/structured-extraction/{structuredProjectId}/thumbnail | 
 *StructuredExtractionProjectManagementApi* | [**patch_api_structured_extraction_structuredprojectid**](docs/StructuredExtractionProjectManagementApi.md#patch_api_structured_extraction_structuredprojectid) | **PATCH** /api/structured-extraction/{structuredProjectId} | 
 *StructuredExtractionProjectManagementApi* | [**patch_api_structured_extraction_structuredprojectid_settings**](docs/StructuredExtractionProjectManagementApi.md#patch_api_structured_extraction_structuredprojectid_settings) | **PATCH** /api/structured-extraction/{structuredProjectId}/settings | 
 *StructuredExtractionProjectManagementApi* | [**post_api_structured_extraction**](docs/StructuredExtractionProjectManagementApi.md#post_api_structured_extraction) | **POST** /api/structured-extraction | 
@@ -396,6 +453,7 @@ Class | Method | HTTP request | Description
 
 ### Documentation For Models
 
+ - [Content](docs/Content.md)
  - [ContentExtractionResponse](docs/ContentExtractionResponse.md)
  - [ContentProjectResponse](docs/ContentProjectResponse.md)
  - [ContentProjectSettingsResponse](docs/ContentProjectSettingsResponse.md)
@@ -409,16 +467,16 @@ Class | Method | HTTP request | Description
  - [FileResponse](docs/FileResponse.md)
  - [HealthResponse](docs/HealthResponse.md)
  - [ImageInfo](docs/ImageInfo.md)
+ - [ImportProjectResponse](docs/ImportProjectResponse.md)
  - [InferenceStatus](docs/InferenceStatus.md)
  - [InferenceValidationError](docs/InferenceValidationError.md)
  - [InformationResponse](docs/InformationResponse.md)
  - [InvalidInformation](docs/InvalidInformation.md)
  - [JobIdResponse](docs/JobIdResponse.md)
- - [JobResponse](docs/JobResponse.md)
  - [JobStatusResponse](docs/JobStatusResponse.md)
- - [PaginatedResponseJobResponse](docs/PaginatedResponseJobResponse.md)
- - [PaginatedResponseStructuredExampleResponse](docs/PaginatedResponseStructuredExampleResponse.md)
+ - [PaginatedResponseT](docs/PaginatedResponseT.md)
  - [ServiceStatus](docs/ServiceStatus.md)
+ - [Structured](docs/Structured.md)
  - [StructuredExampleResponse](docs/StructuredExampleResponse.md)
  - [StructuredExtractionResponse](docs/StructuredExtractionResponse.md)
  - [StructuredInferenceExample](docs/StructuredInferenceExample.md)

{numind-0.2.2 → numind-0.3.1}/README.md

@@ -36,6 +36,7 @@ from numind import NuMindAsync
 client = NuMindAsync(api_key="API_KEY")
 requests = [{}]
 
+
 async def main():
     return [
         await client.extract_structured_data(project_id, **request_kwargs)
@@ -57,14 +58,14 @@ template = {
     "destination": {
         "name": "verbatim-string",
         "zip_code": "string",
-        "country": "string"
+        "country": "string",
     },
     "accommodation": "verbatim-string",
     "activities": ["verbatim-string"],
     "duration": {
         "time_unit": ["day", "week", "month", "year"],
-        "time_quantity": "integer"
-    }
+        "time_quantity": "integer",
+    },
 }
 input_text = """My dream vacation would be a month-long escape to the stunning islands of Tahiti.
 I’d stay in an overwater bungalow in Bora Bora, waking up to crystal-clear turquoise waters and breathtaking sunrises.
@@ -103,7 +104,7 @@ print(output)
 
 ### Create a good template
 
-NuExtract uses JSON schemas as extraction templates which specify the information to retrieve and their types, which are:
+NuExtract uses JSON extraction templates which specify the information to retrieve and their types, which are:
 
 * **string**: a text, whose value can be abstract, i.e. totally free and can be deduced from calculations, reasoning, external knowledge;
 * **verbatim-string**: a purely extractive text whose value must be present in the document. Some flexibility might be allowed on the formatting, e.g. new lines and escaped characters (e.g. `\n`) in a documents might be represented with a space;
@@ -119,7 +120,33 @@ Additionally, the value of a field can be:
 * an **enum**, i.e. a list of elements to choose from of the form `["choice1", "choice2", ...]`. For values of this type, just set the value of the item to choose, e.g. "choice1", and do not set the value as an array containing the item such as `["choice1"]`;
 * a **multi-enum**, i.e. a list from which multiple elements can be picked, of the form `[["choice1", "choice2", ...]]` (double square brackets).
 
-#### Inferring a template
+### Converting JSON schema / Pydantic models to NuExtract template
+
+The SDK offers a method to convert JSON schemas to NuExtract templates:
+
+```Python
+from typing import Literal
+
+from pydantic import Field, BaseModel
+from numind.nuextract_utils import convert_json_schema_to_nuextract_template
+
+
+class HotelBooking(BaseModel):
+    city: str
+    check_in_date: str = Field(description="date")
+    check_out_date: str = Field(description="date")
+    number_of_guests: int
+    room_type: Literal["single", "double", "suite"]
+
+
+template, dropped_branches, descriptions = convert_json_schema_to_nuextract_template(
+    HotelBooking.model_json_schema()
+)
+
+# {'check_in_date': 'date', 'check_out_date': 'date', 'city': 'string', 'number_of_guests': 'integer', 'room_type': ['single', 'double', 'suite']}
+```
+
+### Inferring a template
 
 The "infer_template" method allows to quickly create a template that you can start to work with from a text description.
 
@@ -207,41 +234,52 @@ markdown = client.extract_content(input_file)
 
 ### Extracting Information from Documents
 
-Once your project is ready, you can use it to extract information from documents in real time via this RESTful API.
-
-Each project has its own extraction endpoint:
+Once your structured extraction project is ready, submit a document to the endpoint:
 
-`https://nuextract.ai/api/projects/{projectId}/extract`
+`https://nuextract.ai/api/structured-extraction/{structuredProjectId}/jobs`
 
-You provide it a document and it returns the extracted information according to the task defined in the project. To use it, you need:
+To use it, you need:
 
 - To create an API key in the [Account section](https://nuextract.ai/app/user?content=api)
-- To replace `{projectId}` by the project ID found in the API tab of the project
+- To replace `{structuredProjectId}` by the project ID found in the API tab of the structured extraction project
 
-You can test your extraction endpoint in your terminal using this command-line example with curl (make sure that you replace values of `PROJECT_ID` and `NUEXTRACT_API_KEY`):
+This endpoint creates an asynchronous extraction job. Use the returned `jobId` to retrieve the result from:
+
+`https://nuextract.ai/api/structured-extraction/jobs/{structuredExtractionJobId}`
+
+You can test your extraction endpoint in your terminal using this command-line example with curl (make sure that you replace values of `STRUCTURED_PROJECT_ID` and `NUEXTRACT_API_KEY`):
 
 ```bash
 NUEXTRACT_API_KEY=\"_your_api_key_here_\"; \\
-PROJECT_ID=\"a24fd84a-44ab-4fd4-95a9-bebd46e4768b\"; \\
-curl \"https://nuextract.ai/api/projects/${PROJECT_ID}/extract\" \\
+STRUCTURED_PROJECT_ID=\"a24fd84a-44ab-4fd4-95a9-bebd46e4768b\"; \\
+JOB_ID=$(curl \"https://nuextract.ai/api/structured-extraction/${STRUCTURED_PROJECT_ID}/jobs\" \\
   -X POST \\
   -H \"Authorization: Bearer ${NUEXTRACT_API_KEY}\" \\
-  -H \"Content-Type: application/octet-stream\" \\
-  --data-binary @\"${FILE_NAME}\"
+  -F \"file=@${FILE_NAME}\" | jq -r '.jobId')
+
+curl \"https://nuextract.ai/api/structured-extraction/jobs/${JOB_ID}\" \\
+  -H \"Authorization: Bearer ${NUEXTRACT_API_KEY}\"
 ```
 
 You can also use the [Python SDK](https://github.com/numindai/nuextract-platform-sdk#documentation), by replacing the
-`project_id`, `api_key` and `file_path` variables in the following code:
+`project_id`, `api_key` and request values in the following code:
 
 ```python
-from numind import NuMind
-from pathlib import Path
+import asyncio
+from numind import NuMindAsync
 
-client = NuMind(api_key=api_key)
-file_path = Path(\"path\", \"to\", \"document.odt\")
-with file_path.open(\"rb\") as file:
-    input_file = file.read()
-output_schema = client.post_api_projects_projectid_extract(project_id, input_file)
+client = NuMindAsync(api_key=api_key)
+requests = [{}]
+
+
+async def main():
+    return [
+        await client.extract_structured_data(project_id, **request_kwargs)
+        for request_kwargs in requests
+    ]
+
+
+responses = asyncio.run(main())
 ```
 
 ### Using the Platform via API
@@ -252,26 +290,38 @@ Everything you can do on the web platform can be done via API -
 
 #### Main resources
 
-- **Project** - user project, identified by `projectId`
+- **Structured Extraction Project** - user project for structured extraction, identified by `structuredProjectId`
+- **Content Extraction Project** - user project for content extraction, identified by `contentProjectId`
 - **File** - uploaded file,  identified by `fileId`, stored up to two weeks if not tied to an **Example**
-- **Document** - internal representation of a document, identified by `documentId`, created from a File or a text, stored up to two weeks if not tied to an Example
-- **Example** - document-extraction pair given to teach NuExtract, identified by `exampleId`, created from a Document
+- **Document** - internal representation of a document, identified by `documentId`, created from a File, stored up to two weeks if not tied to an Example
+- **Example** - document-extraction pair given to teach NuExtract, identified by `structuredExampleId`, created from a Document
+- **Job** - asynchronous extraction task, identified by `structuredExtractionJobId`
 
 #### Most common API operations
 
-- Creating a **Project** via `POST /api/projects`
-- Changing the template of a **Project** via `PATCH /api/projects/{projectId}`
+##### Structured extraction
+
+- Creating a **Structured Extraction Project** via `POST /api/structured-extraction`
+- Changing the template of a **Structured Extraction Project** via `PATCH /api/structured-extraction/{structuredProjectId}`
+- Changing settings of a **Structured Extraction Project** via `PATCH /api/structured-extraction/{structuredProjectId}/settings`
+- Uploading a file to a **File** via `POST /api/files` (up to 2 weeks storage)
+- Starting a structured extraction **Job** via `POST /api/structured-extraction/{structuredProjectId}/jobs`
+- Reading a structured extraction **Job** result via `GET /api/structured-extraction/jobs/{structuredExtractionJobId}`
+- Adding an **Example** to a **Structured Extraction Project** via `POST /api/structured-extraction/{structuredProjectId}/examples`
+
+##### Content extraction
+
+- Creating a **Content Extraction Project** via `POST /api/content-extraction`
+- Changing settings of a **Content Extraction Project** via `PATCH /api/content-extraction/{contentProjectId}/settings`
 - Uploading a file to a **File** via `POST /api/files` (up to 2 weeks storage)
-- Creating a **Document** via `POST /api/documents/text` and `POST /api/files/{fileID}/convert-to-document` from a text or a **File**
-- Adding an **Example** to a **Project** via `POST /api/projects/{projectId}/examples`
-- Changing Project settings via `POST /api/projects/{projectId}/settings`
-- Locking a **Project** via `POST /api/projects/{projectId}/lock`
+- Starting a content extraction **Job** via `POST /api/content-extraction/jobs`
+- Reading a content extraction **Job** result via `GET /api/content-extraction/jobs/{contentExtractionJobId}`
 
 This Python package is automatically generated by the [OpenAPI Generator](https://openapi-generator.tech) project:
 
 - API version: 
 - Package version: 1.0.0
-- Generator version: 7.21.0
+- Generator version: 7.22.0
 - Build package: org.openapitools.codegen.languages.PythonClientCodegen
 
 ### Documentation for API Endpoints
@@ -282,6 +332,7 @@ Class | Method | HTTP request | Description
 ------------ | ------------- | ------------- | -------------
 *ContentExtractionApi* | [**get_api_content_extraction_jobs_contentextractionjobid**](docs/ContentExtractionApi.md#get_api_content_extraction_jobs_contentextractionjobid) | **GET** /api/content-extraction/jobs/{contentExtractionJobId} | 
 *ContentExtractionApi* | [**post_api_content_extraction_jobs**](docs/ContentExtractionApi.md#post_api_content_extraction_jobs) | **POST** /api/content-extraction/jobs | 
+*ContentExtractionProjectManagementApi* | [**delete_api_content_extraction_contentprojectid**](docs/ContentExtractionProjectManagementApi.md#delete_api_content_extraction_contentprojectid) | **DELETE** /api/content-extraction/{contentProjectId} | 
 *ContentExtractionProjectManagementApi* | [**get_api_content_extraction**](docs/ContentExtractionProjectManagementApi.md#get_api_content_extraction) | **GET** /api/content-extraction | 
 *ContentExtractionProjectManagementApi* | [**patch_api_content_extraction_contentprojectid**](docs/ContentExtractionProjectManagementApi.md#patch_api_content_extraction_contentprojectid) | **PATCH** /api/content-extraction/{contentProjectId} | 
 *ContentExtractionProjectManagementApi* | [**patch_api_content_extraction_contentprojectid_settings**](docs/ContentExtractionProjectManagementApi.md#patch_api_content_extraction_contentprojectid_settings) | **PATCH** /api/content-extraction/{contentProjectId}/settings | 
@@ -293,7 +344,7 @@ Class | Method | HTTP request | Description
 *DefaultApi* | [**get_api_ping**](docs/DefaultApi.md#get_api_ping) | **GET** /api/ping | 
 *DefaultApi* | [**get_api_version**](docs/DefaultApi.md#get_api_version) | **GET** /api/version | 
 *DocumentsApi* | [**get_api_documents_documentid**](docs/DocumentsApi.md#get_api_documents_documentid) | **GET** /api/documents/{documentId} | 
-*DocumentsApi* | [**get_api_documents_documentid_content**](docs/DocumentsApi.md#get_api_documents_documentid_content) | **GET** /api/documents/{documentId}/content | 
+*DocumentsApi* | [**get_api_documents_documentid_parts_partindex_image**](docs/DocumentsApi.md#get_api_documents_documentid_parts_partindex_image) | **GET** /api/documents/{documentId}/parts/{partIndex}/image | 
 *DocumentsApi* | [**post_api_documents_documentid_new_owner**](docs/DocumentsApi.md#post_api_documents_documentid_new_owner) | **POST** /api/documents/{documentId}/new-owner | 
 *DocumentsApi* | [**post_api_documents_text**](docs/DocumentsApi.md#post_api_documents_text) | **POST** /api/documents/text | 
 *FilesApi* | [**get_api_files_fileid**](docs/FilesApi.md#get_api_files_fileid) | **GET** /api/files/{fileId} | 
@@ -308,6 +359,9 @@ Class | Method | HTTP request | Description
 *JobsApi* | [**get_api_jobs**](docs/JobsApi.md#get_api_jobs) | **GET** /api/jobs | 
 *JobsApi* | [**get_api_jobs_jobid_status**](docs/JobsApi.md#get_api_jobs_jobid_status) | **GET** /api/jobs/{jobId}/status | 
 *JobsApi* | [**get_api_jobs_jobid_stream**](docs/JobsApi.md#get_api_jobs_jobid_stream) | **GET** /api/jobs/{jobId}/stream | 
+*JobsApi* | [**post_api_jobs_jobid_cancel**](docs/JobsApi.md#post_api_jobs_jobid_cancel) | **POST** /api/jobs/{jobId}/cancel | 
+*ProjectImportExportApi* | [**get_api_extraction_projectkind_projectid_export**](docs/ProjectImportExportApi.md#get_api_extraction_projectkind_projectid_export) | **GET** /api/extraction/{projectKind}/{projectId}/export | 
+*ProjectImportExportApi* | [**post_api_extraction_import**](docs/ProjectImportExportApi.md#post_api_extraction_import) | **POST** /api/extraction/import | 
 *StructuredDataExtractionApi* | [**get_api_structured_extraction_jobs_structuredextractionjobid**](docs/StructuredDataExtractionApi.md#get_api_structured_extraction_jobs_structuredextractionjobid) | **GET** /api/structured-extraction/jobs/{structuredExtractionJobId} | 
 *StructuredDataExtractionApi* | [**post_api_structured_extraction_structuredprojectid_jobs**](docs/StructuredDataExtractionApi.md#post_api_structured_extraction_structuredprojectid_jobs) | **POST** /api/structured-extraction/{structuredProjectId}/jobs | 
 *StructuredExtractionExamplesApi* | [**delete_api_structured_extraction_structuredprojectid_examples_structuredexampleid**](docs/StructuredExtractionExamplesApi.md#delete_api_structured_extraction_structuredprojectid_examples_structuredexampleid) | **DELETE** /api/structured-extraction/{structuredProjectId}/examples/{structuredExampleId} | 
@@ -318,6 +372,7 @@ Class | Method | HTTP request | Description
 *StructuredExtractionProjectManagementApi* | [**delete_api_structured_extraction_structuredprojectid**](docs/StructuredExtractionProjectManagementApi.md#delete_api_structured_extraction_structuredprojectid) | **DELETE** /api/structured-extraction/{structuredProjectId} | 
 *StructuredExtractionProjectManagementApi* | [**get_api_structured_extraction**](docs/StructuredExtractionProjectManagementApi.md#get_api_structured_extraction) | **GET** /api/structured-extraction | 
 *StructuredExtractionProjectManagementApi* | [**get_api_structured_extraction_structuredprojectid**](docs/StructuredExtractionProjectManagementApi.md#get_api_structured_extraction_structuredprojectid) | **GET** /api/structured-extraction/{structuredProjectId} | 
+*StructuredExtractionProjectManagementApi* | [**get_api_structured_extraction_structuredprojectid_thumbnail**](docs/StructuredExtractionProjectManagementApi.md#get_api_structured_extraction_structuredprojectid_thumbnail) | **GET** /api/structured-extraction/{structuredProjectId}/thumbnail | 
 *StructuredExtractionProjectManagementApi* | [**patch_api_structured_extraction_structuredprojectid**](docs/StructuredExtractionProjectManagementApi.md#patch_api_structured_extraction_structuredprojectid) | **PATCH** /api/structured-extraction/{structuredProjectId} | 
 *StructuredExtractionProjectManagementApi* | [**patch_api_structured_extraction_structuredprojectid_settings**](docs/StructuredExtractionProjectManagementApi.md#patch_api_structured_extraction_structuredprojectid_settings) | **PATCH** /api/structured-extraction/{structuredProjectId}/settings | 
 *StructuredExtractionProjectManagementApi* | [**post_api_structured_extraction**](docs/StructuredExtractionProjectManagementApi.md#post_api_structured_extraction) | **POST** /api/structured-extraction | 
@@ -333,6 +388,7 @@ Class | Method | HTTP request | Description
 
 ### Documentation For Models
 
+ - [Content](docs/Content.md)
  - [ContentExtractionResponse](docs/ContentExtractionResponse.md)
  - [ContentProjectResponse](docs/ContentProjectResponse.md)
  - [ContentProjectSettingsResponse](docs/ContentProjectSettingsResponse.md)
@@ -346,16 +402,16 @@ Class | Method | HTTP request | Description
  - [FileResponse](docs/FileResponse.md)
  - [HealthResponse](docs/HealthResponse.md)
  - [ImageInfo](docs/ImageInfo.md)
+ - [ImportProjectResponse](docs/ImportProjectResponse.md)
  - [InferenceStatus](docs/InferenceStatus.md)
  - [InferenceValidationError](docs/InferenceValidationError.md)
  - [InformationResponse](docs/InformationResponse.md)
  - [InvalidInformation](docs/InvalidInformation.md)
  - [JobIdResponse](docs/JobIdResponse.md)
- - [JobResponse](docs/JobResponse.md)
  - [JobStatusResponse](docs/JobStatusResponse.md)
- - [PaginatedResponseJobResponse](docs/PaginatedResponseJobResponse.md)
- - [PaginatedResponseStructuredExampleResponse](docs/PaginatedResponseStructuredExampleResponse.md)
+ - [PaginatedResponseT](docs/PaginatedResponseT.md)
  - [ServiceStatus](docs/ServiceStatus.md)
+ - [Structured](docs/Structured.md)
  - [StructuredExampleResponse](docs/StructuredExampleResponse.md)
  - [StructuredExtractionResponse](docs/StructuredExtractionResponse.md)
  - [StructuredInferenceExample](docs/StructuredInferenceExample.md)

numind-0.3.1/docs/Content.md

@@ -0,0 +1,30 @@
+# Content
+
+
+## Properties
+
+Name | Type | Description | Notes
+------------ | ------------- | ------------- | -------------
+**project** | [**ContentProjectResponse**](ContentProjectResponse.md) |  | 
+**type** | **str** |  | 
+
+## Example
+
+```python
+from numind.models.content import Content
+
+# TODO update the JSON string below
+json = "{}"
+# create an instance of Content from a JSON string
+content_instance = Content.from_json(json)
+# print the JSON string representation of the object
+print(Content.to_json())
+
+# convert the object into a dict
+content_dict = content_instance.to_dict()
+# create an instance of Content from a dict
+content_from_dict = Content.from_dict(content_dict)
+```
+[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
+
+