feat: add attribution for pinecone (#3067)

### Summary

- Updates the `pinecone-client` from v2 to v4 using the [client
migration
guide](https://canyon-quilt-082.notion.site/Pinecone-Python-SDK-v3-0-0-Migration-Guide-056d3897d7634bf7be399676a4757c7b#932ad98a2d33432cac4229e1df34d3d5).
Version bump was required to [add
attribution](https://pinecone-2-partner-integration-guide.mintlify.app/integrations/build-integration/attribute-api-activity)
and will also enable use to support [serverless
indexes](https://docs.pinecone.io/reference/pinecone-clients#initialize)
- Adds `"unstructured.{version}"` as the source tag for the connector

### Testing

Destination connection tests
[pass](https://github.com/Unstructured-IO/unstructured/actions/runs/9180305080/job/25244484432?pr=3067)
with the updates.

CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.14.2-dev0
+
+### Enhancements
+
+### Features
+
+  * Add attribution to the `pinecone` connector
+
+### Fixes
+
 ## 0.14.1
 
 ### Enhancements
@@ -13,7 +23,8 @@
   * Use the python client when calling the unstructured api for partitioning or chunking
   * Saving the final content is now a dedicated destination connector (local) set as the default if none are provided. Avoids adding new files locally if uploading elsewhere.
   * Leverage last modified date when deciding if new files should be downloaded and reprocessed.
-* **Add support for Python 3.12**. `unstructured` now works with Python 3.12!
+  * Add attribution to the `pinecone` connector
+  * **Add support for Python 3.12**. `unstructured` now works with Python 3.12!
 
 ### Fixes
 
@@ -47,7 +58,7 @@
 * **Fix disk-space leak in `partition_odt()`.** Remove temporary file created but not removed when `file` argument is passed to `partition_odt()`.
 * **AstraDB: option to prevent indexing metadata**
 * **Fix Missing py.typed**
-  
+
 ## 0.13.7
 
 ### Enhancements

requirements/ingest/embed-huggingface.txt

@@ -152,7 +152,7 @@ requests==2.32.1
     #   transformers
 safetensors==0.4.3
     # via transformers
-scikit-learn==1.4.2
+scikit-learn==1.5.0
     # via sentence-transformers
 scipy==1.11.3
     # via

requirements/ingest/pinecone.in

@@ -1,3 +1,3 @@
 -c ../deps/constraints.txt
 -c ../base.txt
-pinecone-client==2.2.4
+pinecone-client>=3.7.1

requirements/ingest/pinecone.txt

@@ -5,43 +5,12 @@
 #    pip-compile ./ingest/pinecone.in
 #
 certifi==2024.2.2
-    # via
-    #   -c ./ingest/../base.txt
-    #   -c ./ingest/../deps/constraints.txt
-    #   requests
-charset-normalizer==3.3.2
-    # via
-    #   -c ./ingest/../base.txt
-    #   requests
-dnspython==2.6.1
-    # via pinecone-client
-idna==3.7
-    # via
-    #   -c ./ingest/../base.txt
-    #   requests
-loguru==0.7.2
-    # via pinecone-client
-numpy==1.26.4
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   pinecone-client
-pinecone-client==2.2.4
+pinecone-client==4.1.0
     # via -r ./ingest/pinecone.in
-python-dateutil==2.9.0.post0
-    # via
-    #   -c ./ingest/../base.txt
-    #   pinecone-client
-pyyaml==6.0.1
-    # via pinecone-client
-requests==2.32.1
-    # via
-    #   -c ./ingest/../base.txt
-    #   pinecone-client
-six==1.16.0
-    # via
-    #   -c ./ingest/../base.txt
-    #   python-dateutil
 tqdm==4.66.4
     # via
     #   -c ./ingest/../base.txt
@@ -55,4 +24,3 @@ urllib3==1.26.18
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   pinecone-client
-    #   requests

requirements/ingest/salesforce.txt

@@ -48,7 +48,7 @@ requests==2.32.1
     #   requests-toolbelt
     #   simple-salesforce
     #   zeep
-requests-file==2.0.0
+requests-file==2.1.0
     # via zeep
 requests-toolbelt==1.0.0
     # via zeep

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.14.1"  # pragma: no cover
+__version__ = "0.14.2-dev0"  # pragma: no cover

unstructured/ingest/connector/pinecone.py

@@ -72,16 +72,17 @@ class PineconeDestinationConnector(IngestDocSessionHandleMixin, BaseDestinationC
 
     @requires_dependencies(["pinecone"], extras="pinecone")
     def create_index(self) -> "PineconeIndex":
-        import pinecone
+        from pinecone import Pinecone
 
-        pinecone.init(
+        from unstructured import __version__ as unstructured_version
+
+        pc = Pinecone(
             api_key=self.connector_config.access_config.api_key,
-            environment=self.connector_config.environment,
+            source_tag=f"unstructured=={unstructured_version}",
-        )
-        index = pinecone.Index(self.connector_config.index_name)
-        logger.debug(
-            f"Connected to index: {pinecone.describe_index(self.connector_config.index_name)}"
         )
+
+        index = pc.Index(self.connector_config.index_name)
+        logger.debug(f"Connected to index: {pc.describe_index(self.connector_config.index_name)}")
         return index
 
     @DestinationConnectionError.wrap