NIFI-13097 Set project.version in Python Extension Processors

- Enabled resource filtering for Python Extension modules

Signed-off-by: Pierre Villard <pierre.villard.fr@gmail.com>

This closes #8700.
This commit is contained in:
exceptionfactory 2024-04-24 22:50:30 -05:00 committed by Pierre Villard
parent 9ac17833b8
commit 49c8d1b490
No known key found for this signature in database
GPG Key ID: F92A93B30C07C6D5
9 changed files with 9 additions and 7 deletions

View File

@ -35,6 +35,7 @@
<resources>
<resource>
<directory>src/main/python</directory>
<filtering>true</filtering>
<includes>
<include>**/</include>
</includes>

View File

@ -30,7 +30,7 @@ class PromptChatGPT(FlowFileTransform):
implements = ['org.apache.nifi.python.processor.FlowFileTransform']
class ProcessorDetails:
version = '2.0.0-SNAPSHOT'
version = '@project.version@'
description = "Submits a prompt to ChatGPT, writing the results either to a FlowFile attribute or to the contents of the FlowFile"
tags = ["text", "chatgpt", "gpt", "machine learning", "ML", "artificial intelligence", "ai", "document", "langchain"]
dependencies = ['langchain==0.1.2', 'openai==1.9.0', 'jsonpath-ng']

View File

@ -35,6 +35,7 @@
<resources>
<resource>
<directory>src/main/python</directory>
<filtering>true</filtering>
<includes>
<include>**/</include>
</includes>

View File

@ -104,7 +104,7 @@ class ChunkDocument(FlowFileTransform):
class Java:
implements = ['org.apache.nifi.python.processor.FlowFileTransform']
class ProcessorDetails:
version = '2.0.0-SNAPSHOT'
version = '@project.version@'
description = """Chunks incoming documents that are formatted as JSON Lines into chunks that are appropriately sized for creating Text Embeddings.
The input is expected to be in "json-lines" format, with each line having a 'text' and a 'metadata' element.
Each line will then be split into one or more lines in the output."""

View File

@ -45,7 +45,7 @@ class ParseDocument(FlowFileTransform):
implements = ["org.apache.nifi.python.processor.FlowFileTransform"]
class ProcessorDetails:
version = "2.0.0-SNAPSHOT"
version = '@project.version@'
description = """Parses incoming unstructured text documents and performs optical character recognition (OCR) in order to extract text from PDF and image files.
The output is formatted as "json-lines" with two keys: 'text' and 'metadata'.
Note that use of this Processor may require significant storage space and RAM utilization due to third-party dependencies necessary for processing PDF and image files.

View File

@ -26,7 +26,7 @@ class PutChroma(FlowFileTransform):
implements = ['org.apache.nifi.python.processor.FlowFileTransform']
class ProcessorDetails:
version = '2.0.0-SNAPSHOT'
version = '@project.version@'
description = """Publishes JSON data to a Chroma VectorDB. The Incoming data must be in single JSON per Line format, each with two keys: 'text' and 'metadata'.
The text must be a string, while metadata must be a map with strings for values. Any additional fields will be ignored. If the collection name specified
does not exist, the Processor will automatically create the collection."""

View File

@ -52,7 +52,7 @@ class PutPinecone(FlowFileTransform):
implements = ['org.apache.nifi.python.processor.FlowFileTransform']
class ProcessorDetails:
version = '2.0.0-SNAPSHOT'
version = '@project.version@'
description = """Publishes JSON data to Pinecone. The Incoming data must be in single JSON per Line format, each with two keys: 'text' and 'metadata'.
The text must be a string, while metadata must be a map with strings for values. Any additional fields will be ignored."""
tags = ["pinecone", "vector", "vectordb", "vectorstore", "embeddings", "ai", "artificial intelligence", "ml", "machine learning", "text", "LLM"]

View File

@ -27,7 +27,7 @@ class QueryChroma(FlowFileTransform):
implements = ['org.apache.nifi.python.processor.FlowFileTransform']
class ProcessorDetails:
version = '2.0.0-SNAPSHOT'
version = '@project.version@'
description = "Queries a Chroma Vector Database in order to gather a specified number of documents that are most closely related to the given query."
tags = ["chroma", "vector", "vectordb", "embeddings", "enrich", "enrichment", "ai", "artificial intelligence", "ml", "machine learning", "text", "LLM"]

View File

@ -27,7 +27,7 @@ class QueryPinecone(FlowFileTransform):
implements = ['org.apache.nifi.python.processor.FlowFileTransform']
class ProcessorDetails:
version = '2.0.0-SNAPSHOT'
version = '@project.version@'
description = "Queries Pinecone in order to gather a specified number of documents that are most closely related to the given query."
tags = ["pinecone", "vector", "vectordb", "vectorstore", "embeddings", "ai", "artificial intelligence", "ml", "machine learning", "text", "LLM"]