Unstructured-IO · Paul-Cornell · Sep 26, 2024 · Sep 21, 2024 · Sep 23, 2024 · Sep 23, 2024
diff --git a/api-reference/ingest/destination-connector/astradb.mdx b/api-reference/ingest/destination-connector/astradb.mdx
@@ -8,7 +8,7 @@ import SharedAPIKeyURL from '/snippets/general-shared-text/api-key-url.mdx';
 <SharedAstraDB />
 <SharedAPIKeyURL/>
 
-Now call the Unstructured CLI or Python SDK. The source connector can be any of the ones supported. This example uses the local destination connector:
+Now call the Unstructured CLI or Python SDK. The source connector can be any of the ones supported. This example uses the local source connector:
 
 import AstraDBAPISh from '/snippets/destination_connectors/astradb.sh.mdx';
 import AstraDBAPIPyV2 from '/snippets/destination_connectors/astradb.v2.py.mdx';

diff --git a/api-reference/ingest/destination-connector/azure-cognitive-search.mdx b/api-reference/ingest/destination-connector/azure-cognitive-search.mdx
@@ -8,7 +8,7 @@ import SharedAPIKeyURL from '/snippets/general-shared-text/api-key-url.mdx';
 <SharedAzureCS />
 <SharedAPIKeyURL/>
 
-Now call the Unstructured CLI or Python SDK. The source connector can be any of the ones supported. This example uses the local destination connector:
+Now call the Unstructured CLI or Python SDK. The source connector can be any of the ones supported. This example uses the local source connector:
 
 import AzureCSAPISh from '/snippets/destination_connectors/azure_cognitive_search.sh.mdx';
 import AzureCSAPIPyV2 from '/snippets/destination_connectors/azure_cognitive_search.v2.py.mdx';

diff --git a/api-reference/ingest/source-connectors/airtable.mdx b/api-reference/ingest/source-connectors/airtable.mdx
@@ -2,23 +2,24 @@
 title: Airtable
 ---
 
-import SharedContentAirtable from '/snippets/sc-shared-text/airtable.mdx';
+import NewDocument from '/snippets/general-shared-text/new-document.mdx';
+
+<NewDocument />
+
+import SharedContentAirtable from '/snippets/sc-shared-text/airtable-cli-api.mdx';
+import SharedAPIKeyURL from '/snippets/general-shared-text/api-key-url.mdx';
 
 <SharedContentAirtable/>
+<SharedAPIKeyURL/>
 
-Finally, make sure to set the `--partition-by-api` flag and pass in your API key with `--api-key`:
+Now call the Unstructured CLI or Python SDK. The destination connector can be any of the ones supported. This example uses the local destination connector:
 
-import AirtableAPISh from '/snippets/source_connectors/airtable_api.sh.mdx';
-import AirtableAPIPy from '/snippets/source_connectors/airtable_api.py.mdx';
+import AirtableAPISh from '/snippets/source_connectors/airtable.sh.mdx';
+import AirtableAPIPyV2 from '/snippets/source_connectors/airtable.v2.py.mdx';
+import AirtableAPIPyV1 from '/snippets/source_connectors/airtable.v1.py.mdx';
 
 <CodeGroup>
-
   <AirtableAPISh />
-
-  <AirtableAPIPy />
-
-</CodeGroup>
-
-
-Additionally, if you're using Unstructured Serverless API, your locally deployed Unstructured API, or an Unstructured API
-deployed on Azure or AWS, you also need to specify the API URL via the `--partition-endpoint` argument.
+  <AirtableAPIPyV2 />
+  <AirtableAPIPyV1 />
+</CodeGroup>
diff --git a/api-reference/ingest/source-connectors/astradb.mdx b/api-reference/ingest/source-connectors/astradb.mdx
@@ -12,7 +12,7 @@ import SharedAPIKeyURL from '/snippets/general-shared-text/api-key-url.mdx';
 <SharedContentAstraDB/>
 <SharedAPIKeyURL/>
 
-Now call the Unstructured CLI or Python SDK. The source connector can be any of the ones supported. This example uses the local source connector:
+Now call the Unstructured CLI or Python SDK. The destination connector can be any of the ones supported. This example uses the local destination connector:
 
 import AstraDBAPISh from '/snippets/source_connectors/astradb.sh.mdx';
 import AstraDBAPIPyV1 from '/snippets/source_connectors/astradb.v1.py.mdx';

diff --git a/api-reference/ingest/source-connectors/dropbox.mdx b/api-reference/ingest/source-connectors/dropbox.mdx
@@ -12,7 +12,7 @@ import SharedAPIKeyURL from '/snippets/general-shared-text/api-key-url.mdx';
 <SharedContentDropbox/>
 <SharedAPIKeyURL/>
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The source connector can be any of the ones supported. This example uses the local source connector:
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector:
 
 import DropboxAPISh from '/snippets/source_connectors/dropbox.sh.mdx';
 import DropboxAPIPyV2 from '/snippets/source_connectors/dropbox.v2.py.mdx';

diff --git a/api-reference/ingest/source-connectors/hubspot.mdx b/api-reference/ingest/source-connectors/hubspot.mdx
@@ -12,7 +12,7 @@ import SharedAPIKeyURL from '/snippets/general-shared-text/api-key-url.mdx';
 <SharedContentHubSpot/>
 <SharedAPIKeyURL/>
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The source connector can be any of the ones supported. This example uses the local source connector:
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector:
 
 import HubSpotAPISh from '/snippets/source_connectors/hubspot.sh.mdx';
 import HubSpotAPIPyV1 from '/snippets/source_connectors/hubspot.v1.py.mdx';

diff --git a/open-source/ingest/destination-connectors/astradb.mdx b/open-source/ingest/destination-connectors/astradb.mdx
@@ -10,7 +10,7 @@ import SharedAstraDB from '/snippets/dc-shared-text/astradb-cli-api.mdx';
 
 <SharedAstraDB />
 
-Now call the Unstructured CLI or Python. The destination connector can be any of the ones supported. This example uses the local destination connector.
+Now call the Unstructured CLI or Python. The source connector can be any of the ones supported. This example uses the local source connector.
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/destination-connectors/azure-cognitive-search.mdx b/open-source/ingest/destination-connectors/azure-cognitive-search.mdx
@@ -10,7 +10,7 @@ import SharedAzureCS from '/snippets/dc-shared-text/azure-cognitive-search-cli-a
 
 <SharedAzureCS />
 
-Now call the Unstructured CLI or Python. The destination connector can be any of the ones supported. This example uses the local destination connector.
+Now call the Unstructured CLI or Python. The source connector can be any of the ones supported. This example uses the local source connector.
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/destination-connectors/dropbox.mdx b/open-source/ingest/destination-connectors/dropbox.mdx
@@ -10,7 +10,7 @@ import SharedDropbox from '/snippets/dc-shared-text/dropbox-cli-api.mdx';
 
 <SharedDropbox />
 
-Now call the Unstructured Ingest CLI or Unstructured Ingest Python.  The source connector can be any of the ones supported. This example uses the local source connector.
+Now call the Unstructured Ingest CLI or Unstructured Ingest Python. The source connector can be any of the ones supported. This example uses the local source connector.
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/destination-connectors/mongodb.mdx b/open-source/ingest/destination-connectors/mongodb.mdx
@@ -10,7 +10,7 @@ import SharedMongoDB from '/snippets/dc-shared-text/mongodb-cli-api.mdx';
 
 <SharedMongoDB />
 
-Now call the Unstructured Ingest CLI or Unstructured Ingest Python.  The source connector can be any of the ones supported. This example uses the local source connector.
+Now call the Unstructured Ingest CLI or Unstructured Ingest Python. The source connector can be any of the ones supported. This example uses the local source connector.
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/destination-connectors/s3.mdx b/open-source/ingest/destination-connectors/s3.mdx
@@ -10,7 +10,7 @@ import SharedS3 from '/snippets/dc-shared-text/s3-cli-api.mdx';
 
 <SharedS3 />
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The source connector can be any of the ones supported. This example uses the local source connector.
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The source connector can be any of the ones supported. This example uses the local source connector.
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/destination-connectors/sftp.mdx b/open-source/ingest/destination-connectors/sftp.mdx
@@ -10,7 +10,7 @@ import SharedSFTP from '/snippets/dc-shared-text/sftp-cli-api.mdx';
 
 <SharedSFTP />
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The source connector can be any of the ones supported. This example uses the local source connector.
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The source connector can be any of the ones supported. This example uses the local source connector.
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/destination-connectors/singlestore.mdx b/open-source/ingest/destination-connectors/singlestore.mdx
@@ -10,7 +10,7 @@ import SharedSingleStore from '/snippets/dc-shared-text/singlestore-cli-api.mdx'
 
 <SharedSingleStore />
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The source connector can be any of the ones supported. This example uses the local source connector.
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The source connector can be any of the ones supported. This example uses the local source connector.
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/destination-connectors/weaviate.mdx b/open-source/ingest/destination-connectors/weaviate.mdx
@@ -10,7 +10,7 @@ import SharedWeaviate from '/snippets/dc-shared-text/weaviate-cli-api.mdx';
 
 <SharedWeaviate />
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The source connector can be any of the ones supported. This example uses the local source connector:
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The source connector can be any of the ones supported. This example uses the local source connector:
 
 This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/source-connectors/airtable.mdx b/open-source/ingest/source-connectors/airtable.mdx
@@ -2,21 +2,28 @@
 title: Airtable
 ---
 
-import SharedContentAirtable from '/snippets/sc-shared-text/airtable.mdx';
+import NewDocument from '/snippets/general-shared-text/new-document.mdx';
+
+<NewDocument />
+
+import SharedContentAirtable from '/snippets/sc-shared-text/airtable-cli-api.mdx';
 
 <SharedContentAirtable/>
 
+Now call the Unstructured CLI or Python. The destination connector can be any of the ones supported. This example uses the local destination connector.
+
+This example sends data to Unstructured API services for processing by default. To process data locally instead, see the instructions at the end of this page.
 
 import AirtableSh from '/snippets/source_connectors/airtable.sh.mdx';
-import AirtablePy from '/snippets/source_connectors/airtable.py.mdx';
+import AirtablePyV2 from '/snippets/source_connectors/airtable.v2.py.mdx';
+import AirtablePyV1 from '/snippets/source_connectors/airtable.v1.py.mdx';
 
 <CodeGroup>
-
   <AirtableSh />
-
-  <AirtablePy />
-
+  <AirtablePyV2 />
+  <AirtablePyV1 />
 </CodeGroup>
 
+import SharedPartitionByAPIOSS from '/snippets/ingest-configuration-shared/partition-by-api-oss.mdx';
 
-For a full list of the options that the Unstructured Ingest CLI accepts check `unstructured-ingest airtable --help`.
+<SharedPartitionByAPIOSS/>
diff --git a/open-source/ingest/source-connectors/astradb.mdx b/open-source/ingest/source-connectors/astradb.mdx
@@ -10,7 +10,7 @@ import SharedContentAstraDB from '/snippets/sc-shared-text/astradb-cli-api.mdx';
 
 <SharedContentAstraDB/>
 
-Now call the Unstructured CLI or Python. The source connector can be any of the ones supported. This example uses the local source connector.
+Now call the Unstructured CLI or Python. The destination connector can be any of the ones supported. This example uses the local destination connector.
 
 This example sends data to Unstructured API services for processing by default. To process data locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/source-connectors/azure.mdx b/open-source/ingest/source-connectors/azure.mdx
@@ -10,7 +10,7 @@ import SharedContentAzure from '/snippets/sc-shared-text/azure-cli-api.mdx';
 
 <SharedContentAzure/>
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The destination connector can be any of the ones supported. This example uses the local destination connector.
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector.
 
 This example sends data to Unstructured API services for processing by default. To process data locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/source-connectors/dropbox.mdx b/open-source/ingest/source-connectors/dropbox.mdx
@@ -10,7 +10,7 @@ import SharedContentDropbox from '/snippets/sc-shared-text/dropbox-cli-api.mdx';
 
 <SharedContentDropbox/>
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The destination connector can be any of the ones supported. This example uses the local destination connector.
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector.
 
 This example sends data to Unstructured API services for processing by default. To process data locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/source-connectors/mongodb.mdx b/open-source/ingest/source-connectors/mongodb.mdx
@@ -10,7 +10,7 @@ import SharedContentMongoDB from '/snippets/sc-shared-text/mongodb-cli-api.mdx';
 
 <SharedContentMongoDB/>
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The destination connector can be any of the ones supported. This example uses the local destination connector:
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector:
 
 This example sends data to Unstructured API services for processing by default. To process data locally instead, see the instructions at the end of this page.
 

diff --git a/open-source/ingest/source-connectors/one-drive.mdx b/open-source/ingest/source-connectors/one-drive.mdx
@@ -10,7 +10,7 @@ import SharedContentOneDrive from '/snippets/sc-shared-text/onedrive-cli-api.mdx
 
 <SharedContentOneDrive/>
 
-Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library.  The destination connector can be any of the ones supported. This example uses the local destination connector:
+Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector:
 
 This example sends data to Unstructured API services for processing by default. To process data locally instead, see the instructions at the end of this page.
 

diff --git a/snippets/general-shared-text/airtable-cli-api.mdx b/snippets/general-shared-text/airtable-cli-api.mdx
@@ -0,0 +1,14 @@
+The Airtable connector dependencies:
+
+```bash CLI, Python
+pip install "unstructured-ingest[airtable]"
+```
+
+import AdditionalIngestDependencies from '/snippets/general-shared-text/ingest-dependencies.mdx';
+
+<AdditionalIngestDependencies />
+
+These environment variables:
+
+- `AIRTABLE_TOKEN` - The Airtable personal access token, represented by `--personal-access-token` (CLI) or `personal_access_token` (Python).
+- `AIRTABLE_PATHS` - The list of Airtable paths to process, represented by `--list-of-paths` (CLI) or `list_of_paths` (Python).
diff --git a/snippets/general-shared-text/airtable.mdx b/snippets/general-shared-text/airtable.mdx
@@ -0,0 +1,27 @@
+The Airtable connector prerequisites:
+
+- An [Airtable](https://www.airtable.com/) account. [Create a free Airtable account](https://airtable.com/signup). 
+- An Airtable personal access token. [Create a personal access token](https://support.airtable.com/docs/creating-and-using-api-keys-and-access-tokens).
+- The ID of the Airtable base to access. [Create a base](https://www.airtable.com/guides/build/create-a-base). [Get a base's ID](https://support.airtable.com/docs/finding-airtable-ids#finding-base-url-ids).
+- The ID of the table to access in the base. [Create a table](https://www.airtable.com/guides/build/create-a-table). [Get a table's ID](https://support.airtable.com/docs/finding-airtable-ids#finding-base-url-ids).
+- The ID of the view to access in the table. [Create a view](https://www.airtable.com/guides/build/create-custom-views-of-data). [Get a view's ID](https://support.airtable.com/docs/finding-airtable-ids#finding-base-url-ids).
+
+By default, Unstructured processes all tables from all bases within an Airtable organization. You can limit the 
+tables that Unstructured ingests data from within Airtable by specifying a list of Airtable paths. 
+An Airtable path uses the following structure: `base_id/table_id(optional)/view_id(optional)`
+
+For example, given the following example Airtable URL:
+
+```text
+https://airtable.com/appr9nKeXLAtg6bgn/tblZ8uT1GY7NLbWit/viwDcpzf9dP0Gqz5J
+```
+
+- The base's ID is `appr9nKeXLAtg6bgn`. The base's path is `appr9nKeXLAtg6bgn`.
+- The table's ID is `tblZ8uT1GY7NLbWit`. The table's path is `appr9nKeXLAtg6bgn/tblZ8uT1GY7NLbWit`.
+- The view's ID is `viwDcpzf9dP0Gqz5J`. The view's path is `appr9nKeXLAtg6bgn/tblZ8uT1GY7NLbWit/viwDcpzf9dP0Gqz5J`.
+
+You can call the Airtable API to get lists of available IDs for Airtable bases, tables, and views in bulk, as follows:
+
+- [Base IDs](https://airtable.com/developers/web/api/list-bases)
+- [Table and view IDs](https://airtable.com/developers/web/api/get-base-schema)
+- [Base, table, and view IDs](https://pyairtable.readthedocs.io/en/latest/metadata.html)
diff --git a/snippets/sc-shared-text/airtable-cli-api.mdx b/snippets/sc-shared-text/airtable-cli-api.mdx
@@ -0,0 +1,9 @@
+Connect Airtable to your preprocessing pipeline, and use the Unstructured Ingest CLI or the Unstructured Ingest Python library to batch process all your data and store structured outputs locally on your filesystem.
+
+You will need: 
+
+import AirtableShared from '/snippets/general-shared-text/airtable.mdx';
+import AirtableSharedCLIAPI from '/snippets/general-shared-text/airtable-cli-api.mdx';
+
+<AirtableShared />
+<AirtableSharedCLIAPI />
diff --git a/snippets/sc-shared-text/airtable.mdx b/snippets/sc-shared-text/airtable.mdx
diff --git a/snippets/source_connectors/airtable.py.mdx b/snippets/source_connectors/airtable.py.mdx
diff --git a/snippets/source_connectors/airtable.sh.mdx b/snippets/source_connectors/airtable.sh.mdx
@@ -1,12 +1,13 @@
-```bash Shell
+```bash CLI
 #!/usr/bin/env bash
 
 unstructured-ingest \
   airtable \
-    --metadata-exclude filename,file_directory,metadata.data_source.date_processed \
     --personal-access-token $AIRTABLE_PERSONAL_ACCESS_TOKEN \
     --output-dir $LOCAL_FILE_OUTPUT_DIR \
     --num-processes 2 \
     --reprocess \
-    --strategy hi_res
+    --partition-by-api \
+    --api-key $UNSTRUCTURED_API_KEY \
+    --partition-endpoint $UNSTRUCTURED_API_URL
 ```