Merge branch 'development' into shanepeckham/content-sampling#330

.github/workflows/build_validation_workflow.yml

@@ -22,7 +22,7 @@ jobs:
     steps:
       - name: Checkout Actions
         uses: actions/checkout@v4
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.11"
       - name: Load all build validation related dependencies
@@ -31,7 +31,7 @@ jobs:
           set -e # fail on error
           python -m pip install --upgrade pip
           python -m pip install -e . -r requirements.txt -r dev-requirements.txt
-          
+
       - name: Run flake
         shell: bash
         run: |
@@ -43,7 +43,7 @@ jobs:
           pytest . --cov=. --cov-report=html --cov-config=.coveragerc
 
       - name: Publish Unit Test Results
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: unit-test-results
           path: "htmlcov/**"

.github/workflows/rag_exp_acc_ci.yml

@@ -23,7 +23,7 @@ jobs:
       AZURE_SEARCH_ADMIN_KEY: ${{ secrets.AZURE_SEARCH_ADMIN_KEY }}
       AZURE_SEARCH_SERVICE_ENDPOINT: ${{ secrets.AZURE_SEARCH_SERVICE_ENDPOINT }}
       AZURE_LANGUAGE_SERVICE_KEY: ${{ secrets.AZURE_LANGUAGE_SERVICE_KEY }}
-      AZURE_LANGUAGE_SERVICE_ENDPOINT: ${{ secrets.AZURE_LANGUAGE_SERVICE_ENDPOINT }}      
+      AZURE_LANGUAGE_SERVICE_ENDPOINT: ${{ secrets.AZURE_LANGUAGE_SERVICE_ENDPOINT }}
       OPENAI_API_TYPE: "azure"
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       OPENAI_API_VERSION: ${{ secrets.OPENAI_API_VERSION }}
@@ -39,7 +39,7 @@ jobs:
       - name: Checkout Actions
         uses: actions/checkout@v4
       - name: Azure login
-        uses: azure/login@v1
+        uses: azure/login@v2
         with:
           creds: ${{ secrets.azure_credentials }}
       - name: Configure Azure ML Agent
@@ -51,11 +51,11 @@ jobs:
       - name: execute qna step
         shell: bash
         run: |
-          python 02_qa_generation.py  
+          python 02_qa_generation.py
       - name: execute querying step
         shell: bash
         run: |
-          python 03_querying.py  
+          python 03_querying.py
       - name: execute evaluation step
         shell: bash
         run: |

dev-requirements.txt

@@ -1,7 +1,7 @@
-promptflow==1.1.1
-promptflow-tools==1.0.0
+promptflow==1.6.0
+promptflow-tools==1.3.0
 pytest==8.1.1
 pytest-cov==4.1.0
 flake8==7.0.0
-pre-commit==3.5.0
+pre-commit==3.6.2
 black==24.2.0

rag_experiment_accelerator/embedding/st_embedding_model.py

@@ -1,4 +1,3 @@
-from requests import HTTPError
 from sentence_transformers import SentenceTransformer
 from rag_experiment_accelerator.embedding.embedding_model import EmbeddingModel
 
@@ -55,7 +54,7 @@ def __init__(self, model_name: str, dimension: int = None, **kwargs) -> None:
         super().__init__(name=model_name, dimension=dimension, **kwargs)
         try:
             self._model = SentenceTransformer(self.name)
-        except HTTPError as e:
+        except OSError as e:
             logger.error(
                 f"Error retrieving model: {self.name}. Please check that the model name is correct and that you have an internet connection."
             )

rag_experiment_accelerator/embedding/tests/test_st_embedding_model.py

@@ -1,7 +1,6 @@
 from unittest.mock import patch
 import pytest
 import numpy as np
-from requests import HTTPError
 from rag_experiment_accelerator.embedding.st_embedding_model import STEmbeddingModel
 
 
@@ -18,7 +17,7 @@ def test_generate_embedding(mock_sentence_transformer):
 
 
 def test_sentence_transformer_embedding_model_raises_non_existing_model():
-    with pytest.raises(HTTPError):
+    with pytest.raises(OSError):
         STEmbeddingModel("non-existing-model", 123)
 
 

requirements.txt

@@ -1,36 +1,37 @@
-PyPDF2~=2.0
-azure-core==1.29.4
-matplotlib==3.8.0
-plotly==5.18.0
-tiktoken==0.5.1
-openai==1.3.7
-spacy==3.7.2
-scikit-learn==1.3.2
-pytesseract==0.3.10
+azure-ai-ml==1.14.0
+azure-ai-textanalytics==5.3.0
+azure-core==1.30.1
+azure-identity==1.15.0
+azure-keyvault-secrets==4.8.*
 azure-search-documents==11.4.b11
-python-dotenv==1.0.0
-PyMuPDF==1.23.5
+azure.ai.documentintelligence==1.0.0b2
+azureml-mlflow==1.55.0
+beautifulsoup4==4.12.3
+datasets==2.18.0
 docx2txt==0.8
-azure-ai-ml==1.11.1
-azure-identity==1.14.1
-textdistance==4.6.0
-azureml-mlflow==1.53.0
-fuzzywuzzy==0.18.0
-mlflow==2.10.0
-rouge-score==0.1.2
-hnswlib==0.7.0
-pypdf==3.17.0
-langchain==0.0.329
-langchain-community==0.0.16
-sentence-transformers==2.2.2
-beautifulsoup4==4.12.2
-lxml==4.9.3
-unstructured==0.10.26
-datasets==2.14.6
 evaluate==0.4.1
-azure-ai-textanalytics==5.3.0
-azure.ai.documentintelligence==1.0.0b1
+fuzzywuzzy==0.18.0
+hnswlib==0.8.0
+langchain==0.1.9
+langchain-community==0.0.28
 levenshtein==0.25.0
 umap-learn==0.5.5
 kaleido==0.2.1
-azure-keyvault-secrets==4.4.*
+azure-keyvault-secrets==4.4.*
+lxml==5.1.0
+matplotlib==3.8.3
+mlflow==2.11.1
+openai==1.13.3
+plotly==5.19.0
+pypdf==4.1.0
+pytesseract==0.3.10
+python-dotenv==1.0.1
+PyMuPDF==1.23.26
+PyPDF2~=3.0
+rouge-score==0.1.2
+scikit-learn==1.4.1post1
+sentence-transformers==2.5.1
+spacy==3.7.4
+textdistance==4.6.1
+tiktoken==0.6.0
+unstructured==0.11.8