krisztina-zsihovszki commented on code in PR #8441: URL: https://github.com/apache/nifi/pull/8441#discussion_r1500550037
########## nifi-python-extensions/nifi-text-embeddings-module/src/main/python/vectorstores/PutOpenSearchVector.py: ########## @@ -0,0 +1,251 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from langchain.vectorstores import OpenSearchVectorSearch +from nifiapi.flowfiletransform import FlowFileTransform, FlowFileTransformResult +from nifiapi.properties import PropertyDescriptor, StandardValidators, ExpressionLanguageScope, PropertyDependency +from OpenSearchVectorUtils import (OPENAI_API_KEY, OPENAI_API_MODEL, HUGGING_FACE_API_KEY, HUGGING_FACE_MODEL, + HTTP_HOST, + USERNAME, PASSWORD, VERIFY_CERTIFICATES, INDEX_NAME, VECTOR_FIELD, TEXT_FIELD, + create_authentication_params, parse_documents) +from EmbeddingUtils import EMBEDDING_MODEL, create_embedding_service +from nifiapi.documentation import use_case, multi_processor_use_case, ProcessorConfiguration + + +@use_case(description="Create vectors/embeddings that represent text content and send the vectors to OpenSearch", + notes="This use case assumes that the data has already been formatted in JSONL format with the text to store in OpenSearch provided in the 'text' field.", + keywords=["opensearch", "embedding", "vector", "text", "vectorstore", "insert"], + configuration=""" + Configure the 'HTTP Host' to an appropriate URL where OpenSearch is accessible. + Configure 'Embedding Model' to indicate whether OpenAI embeddings should be used or a HuggingFace embedding model should be used: 'Hugging Face Model' or 'OpenAI Model' + Configure the 'OpenAI API Key' or 'HuggingFace API Key', depending on the chosen Embedding Model. + Set 'Index Name' to the name of your OpenSearch Index. + Set 'Vector Field Name' to the name of the field in the Document which will store the vector data. + Set 'Text Field Name' to the name of the field in the Document which will store the text data. + + If the documents to send to OpenSearch contain a unique identifier, set the 'Document ID Field Name' property to the name of the field that contains the document ID. + This property can be left blank, in which case a unique ID will be generated based on the FlowFile's filename. + + If the provided index does not exists in OpenSearch then the processor is capable to create it. The 'New Index Strategy' property defines + that the index needs to be created from the default template or it should be configured with custom values. + """) +@use_case(description="Update vectors/embeddings in OpenSearch", + notes="This use case assumes that the data has already been formatted in JSONL format with the text to store in OpenSearch provided in the 'text' field.", + keywords=["opensearch", "embedding", "vector", "text", "vectorstore", "update", "upsert"], + configuration=""" + Configure the 'HTTP Host' to an appropriate URL where OpenSearch is accessible. + Configure 'Embedding Model' to indicate whether OpenAI embeddings should be used or a HuggingFace embedding model should be used: 'Hugging Face Model' or 'OpenAI Model' + Configure the 'OpenAI API Key' or 'HuggingFace API Key', depending on the chosen Embedding Model. + Set 'Index Name' to the name of your OpenSearch Index. + Set 'Vector Field Name' to the name of the field in the Document which will store the vector data. + Set 'Text Field Name' to the name of the field in the Document which will store the text data. + Set the 'Document ID Field Name' property to the name of the field that contains the identifier of the document in OpenSearch to update. + """) +class PutOpenSearchVector(FlowFileTransform): + class Java: + implements = ['org.apache.nifi.python.processor.FlowFileTransform'] + + class ProcessorDetails: + version = '2.0.0-SNAPSHOT' + description = """Publishes JSON data to OpenSearch. 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 = ["opensearch", "vector", "vectordb", "vectorstore", "embeddings", "ai", "artificial intelligence", "ml", + "machine learning", "text", "LLM"] + + # Engine types + NMSLIB = ("nmslib (Non-Metric Space Library)", "nmslib") + FAISS = ("faiss (Facebook AI Similarity Search)", "faiss") + LUCENE = ("lucene", "lucene") + + ENGINE_VALUES = dict([NMSLIB, FAISS, LUCENE]) + + # Space types + L2 = ("L2 (Euclidean distance)", "l2") Review Comment: The space types (L2, L1, LINF, COSINESIMIL) seem to be the same for PutOpenSearchVector.py and QueryOpenSearchVector.py, those can be extracted to OpenSearchVectorUtils.py. ########## nifi-python-extensions/nifi-text-embeddings-module/src/main/python/vectorstores/OpenSearchVectorUtils.py: ########## @@ -0,0 +1,149 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from nifiapi.properties import PropertyDescriptor, StandardValidators, ExpressionLanguageScope, PropertyDependency +from EmbeddingUtils import OPENAI, HUGGING_FACE, EMBEDDING_MODEL + +HUGGING_FACE_API_KEY = PropertyDescriptor( + name="HuggingFace API Key", + description="The API Key for interacting with HuggingFace", + required=True, + sensitive=True, + validators=[StandardValidators.NON_EMPTY_VALIDATOR], + dependencies=[PropertyDependency(EMBEDDING_MODEL, HUGGING_FACE)] +) +HUGGING_FACE_MODEL = PropertyDescriptor( + name="HuggingFace Model", + description="The name of the HuggingFace model to use", + default_value="sentence-transformers/all-MiniLM-L6-v2", + required=True, + validators=[StandardValidators.NON_EMPTY_VALIDATOR], + dependencies=[PropertyDependency(EMBEDDING_MODEL, HUGGING_FACE)] +) +OPENAI_API_KEY = PropertyDescriptor( + name="OpenAI API Key", + description="The API Key for OpenAI in order to create embeddings", + required=True, + sensitive=True, + validators=[StandardValidators.NON_EMPTY_VALIDATOR], + dependencies=[PropertyDependency(EMBEDDING_MODEL, OPENAI)] +) +OPENAI_API_MODEL = PropertyDescriptor( + name="OpenAI Model", + description="The API Key for OpenAI in order to create embeddings", + default_value="text-embedding-ada-002", + required=True, + validators=[StandardValidators.NON_EMPTY_VALIDATOR], + dependencies=[PropertyDependency(EMBEDDING_MODEL, OPENAI)] +) +HTTP_HOST = PropertyDescriptor( + name="HTTP Host", + description="URL where OpenSearch is hosted.", + default_value="http://localhost:9200";, + required=True, + validators=[StandardValidators.NON_EMPTY_VALIDATOR] +) +USERNAME = PropertyDescriptor( + name="Username", + description="The username to use for authenticating to OpenSearch server", + required=False, + validators=[StandardValidators.NON_EMPTY_VALIDATOR] +) +PASSWORD = PropertyDescriptor( + name="Password", + description="The password to use for authenticating to OpenSearch server", + required=False, + sensitive=True, + validators=[StandardValidators.NON_EMPTY_VALIDATOR] +) +VERIFY_CERTIFICATES = PropertyDescriptor( + name="Verify Certificates", + description="The password to use for authenticating to OpenSearch server", + allowable_values=["true", "false"], + default_value="false", + required=False, + validators=[StandardValidators.NON_EMPTY_VALIDATOR] +) +INDEX_NAME = PropertyDescriptor( + name="Index Name", + description="The name of the OpenSearch index.", + sensitive=False, + required=True, + validators=[StandardValidators.NON_EMPTY_VALIDATOR], + expression_language_scope=ExpressionLanguageScope.FLOWFILE_ATTRIBUTES +) +VECTOR_FIELD = PropertyDescriptor( + name="Vector Field Name", + description="The name of Document field where the embeddings are stored. This field need to be a 'knn_vector' typed field.", Review Comment: Please use "document" here as well (as it is done in other descriptions) -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@nifi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
