fix: improve doc code (#2920)

Improves the documentation code.
Standardizes unstructured api key
Replaces misc hard coded values
Replaces `azureunstructured1` with a generic value

Author: potter-potter

CHANGELOG.md

@@ -12,5 +12,5 @@ unstructured-ingest \
   --num-processes 2 \
   --verbose \
   azure \
-  --account-name azureunstructured1 \
+  --account-name "$AZURE_ACCOUNT_NAME" \
   --remote-url "<your destination path here, ie 'az://unstructured/war-and-peace-output'>"

docs/source/ingest/destination_connectors/code/bash/azure.sh

@@ -9,7 +9,7 @@ unstructured-ingest \
   --num-processes 2 \
   --verbose \
   clarifai \
-  --app-id "<your clarifai app name>" \
-  --user-id "<your clarifai user id>" \
-  --api-key "<your clarifai PAT key>" \
+  --app-id "$CLARIFAI_APP_ID" \
+  --user-id "$CLARIFAI_USER_ID" \
+  --api-key "$CLARIFAI_PAT_KEY" \
   --batch-size 100

docs/source/ingest/destination_connectors/code/bash/clarifai.sh

@@ -12,6 +12,6 @@ unstructured-ingest \
   --num-processes 2 \
   --verbose \
   qdrant \
-  --collection-name "test" \
+  --collection-name "$QDRANT_COLLECTION_NAME" \
   --location "http://localhost:6333" \
   --batch-size 80

docs/source/ingest/destination_connectors/code/bash/qdrant.sh

@@ -1,3 +1,5 @@
+import os
+
 from unstructured.ingest.connector.fsspec.azure import (
     AzureAccessConfig,
     AzureWriteConfig,
@@ -21,7 +23,7 @@
 def get_writer() -> Writer:
     return AzureWriter(
         connector_config=SimpleAzureBlobStorageConfig(
-            access_config=AzureAccessConfig(account_name="azureunstructured1"),
+            access_config=AzureAccessConfig(account_name=os.getenv("AZURE_ACCOUNT_NAME")),
             remote_url="az://unstructured/war-and-peace-output",
         ),
         write_config=AzureWriteConfig(),

docs/source/ingest/destination_connectors/code/python/azure.py

@@ -1,3 +1,5 @@
+import os
+
 from unstructured.ingest.connector.clarifai import (
     ClarifaiAccessConfig,
     ClarifaiWriteConfig,
@@ -20,9 +22,9 @@
 def get_writer() -> Writer:
     return ClarifaiWriter(
         connector_config=SimpleClarifaiConfig(
-            access_config=ClarifaiAccessConfig(api_key="CLARIFAI_PAT"),
-            app_id="CLARIFAI_APP",
-            user_id="CLARIFAI_USER_ID",
+            access_config=ClarifaiAccessConfig(api_key=os.getenv("CLARIFAI_PAT_KEY")),
+            app_id=os.getenv("CLARIFAI_APP_ID"),
+            user_id=os.getenv("CLARIFAI_USER_ID"),
         ),
         write_config=ClarifaiWriteConfig(),
     )

docs/source/ingest/destination_connectors/code/python/clarifai.py

@@ -8,4 +8,4 @@ unstructured-ingest \
   --num-processes 2 \
   --reprocess \
   --partition-by-api \
-  --api-key "<UNSTRUCTURED-API-KEY>"
+  --api-key "$UNSTRUCTURED_API_KEY"

docs/source/ingest/source_connectors/code/bash/airtable_api.sh

@@ -3,6 +3,6 @@
 unstructured-ingest \
   azure \
   --remote-url abfs://container1/ \
-  --account-name azureunstructured1 \
+  --account-name "$AZURE_ACCOUNT_NAME" \
   --output-dir azure-ingest-output \
   --num-processes 2

docs/source/ingest/source_connectors/code/bash/azure.sh

@@ -3,8 +3,8 @@
 unstructured-ingest \
   azure \
   --remote-url abfs://container1/ \
-  --account-name azureunstructured1 \
+  --account-name "$AZURE_ACCOUNT_NAME" \
   --output-dir azure-ingest-output \
   --num-processes 2 \
   --partition-by-api \
-  --api-key "<UNSTRUCTURED-API-KEY>"
+  --api-key "$UNSTRUCTURED_API_KEY"

docs/source/ingest/source_connectors/code/bash/azure_api.sh

@@ -8,4 +8,4 @@ unstructured-ingest \
   --verbose \
   --preserve-downloads \
   --partition-by-api \
-  --api-key "<UNSTRUCTURED-API-KEY>"
+  --api-key "$UNSTRUCTURED_API_KEY"