Merge branch 'main' into feature/small-improvements

Author: strickvl

.github/workflows/production_run_complete_llm.yml

@@ -13,6 +13,7 @@ concurrency:
 jobs:
   run-production-workflow:
     runs-on: ubuntu-latest
+    if: github.event.pull_request.draft == false
     env:
       ZENML_STORE_URL: ${{ secrets.ZENML_PROJECTS_HOST }}
       ZENML_STORE_API_KEY: ${{ secrets.ZENML_PROJECTS_API_KEY }}
@@ -56,4 +57,4 @@ jobs:
       - name: Run pipeline, create pipeline, configure trigger (Production)
         working-directory: ./llm-complete-guide
         run: |
-          python gh_action_rag.py --no-cache --create-template --event-source-id ${{ env.ZENML_EVENT_SOURCE_ID }} --service-account-id ${{ env.ZENML_SERVICE_ACCOUNT_ID }} --config production/rag.yaml --zenml-model-version production
+          python gh_action_rag.py --no-cache --create-template --event-source-id ${{ env.ZENML_EVENT_SOURCE_ID }} --service-account-id ${{ env.ZENML_SERVICE_ACCOUNT_ID }} --config production/rag.yaml --zenml-model-version production

.github/workflows/pull_request.yml

@@ -8,6 +8,7 @@ jobs:
   spell-check:
     name: spell-check
     runs-on: ubuntu-latest
+    if: github.event.pull_request.draft == false
     env:
       ZENML_DEBUG: 1
       ZENML_ANALYTICS_OPT_IN: false
@@ -23,3 +24,4 @@ jobs:
 
   markdown-link-check:
     uses: ./.github/workflows/markdown-link-check.yml
+    if: github.event.pull_request.draft == false

.github/workflows/staging_run_complete_llm.yml

@@ -11,6 +11,7 @@ concurrency:
 jobs:
   run-staging-workflow:
     runs-on: ubuntu-latest
+    if: github.event.pull_request.draft == false
     env:
       ZENML_STORE_URL: ${{ secrets.ZENML_PROJECTS_HOST }}
       ZENML_STORE_API_KEY: ${{ secrets.ZENML_PROJECTS_API_KEY }}
@@ -52,4 +53,4 @@ jobs:
       - name: Run pipeline (Staging)
         working-directory: ./llm-complete-guide
         run: |
-          python gh_action_rag.py --no-cache --config staging/rag.yaml --zenml-model-version staging
+          python gh_action_rag.py --no-cache --config staging/rag.yaml --zenml-model-version staging

README.md

@@ -59,25 +59,19 @@ etc.
 
 A list of updated and maintained projects by the ZenML team and the community:
 
-| Project                                                                | Tags                                  | Integrations                                                             |
-|------------------------------------------------------------------------|---------------------------------------|--------------------------------------------------------------------------|
-| [NBA Three-Pointer Predictor](nba-pipeline)                            | Time-series                           | `mlflow` `kubeflow` `evidently` `sklearn` `aws`                          |
-| [Time Series Forecasting](time-series-forecast)                        | Time-series                           | `gcp`                                                                    |
-| [Customer Satisfaction](customer-satisfaction)                         | Tabular                               | `mlflow` `kubeflow`                                                      |
-| [Customer Churn](customer-churn)                                       | Tabular                               | `kubeflow` `seldon`                                                      |
-| [Label Studio Annotation](label_studio_annotation)                     | Data Annotation                       | `label-studio`                                                           | 
-| [YOLOv5 Object Detection](sign-language-detection-yolov5)              | Computer-vision                       | `mlflow` `gcp`                                                           |
-| [LLMs To Analyze Databases](supabase-openai-summary)                   | NLP, LLMs                             | `gcp` `slack`                                                            |
-| [GitFlow ZenML Project](https://github.com/zenml-io/zenml-gitflow)     | MLOps with ZenML and GitHub Workflows | `mlflow` `deepchecks` `kserve` `kubeflow` `sklearn` `vertex` `aws` `gcp` |
-| [ZenNews](zen-news-summarization)                                      | NLP                                   | `gcp` `vertex` `discord`                                                 |
-| [LLM RAG Pipeline with Langchain and OpenAI](llm-agents/)                    | NLP, LLMs                             | `slack` `langchain` `llama_index`                                        |
-| [Orbit User Analysis](orbit-user-analysis)                             | Data Analysis, Tabular                | -                                                                        |
-| [Huggingface to Sagemaker](huggingface-sagemaker)                      | NLP                                   | `pytorch` `mlflow` `huggingface` `aws` `s3` `kubeflow` `slack` `github`  |
-| [Complete Guide to LLMs (from RAG to finetuning)](llm-complete-guide)               | NLP, LLMs, embeddings, finetuning                           | `openai` `supabase` `huggingface` `argilla`  |
-| [LLM LoRA Finetuning (Phi3 and Llama 3.1)](llm-lora-finetuning)               | NLP, LLMs                           | `gcp`  |
-| [ECP Price Prediction with GCP Cloud Composer](airflow-cloud-composer-etl-feature-train/README.md)               | Regression, Airflow                           | `cloud-composer` `airflow` |
-| [Simple LLM finetuning with Lightning Studio](simple-llm-finetuning/README.md)               | Lightning AI Studio, LLMs                           | `cloud-composer` `airflow` |
-| [Flux Dreambooth](flux-dreambooth/README.md)               | Flux, Dreambooth, LLMs                           | `modal` `kubernetes` |
+| Project | Tags | Tools |
+|---------|------|-------|
+| [LLM Agents](llm-agents) | `NLP` `LLM Agents` `Conversational AI` `RAG` `Vector Stores` `Production MLOps` | `langchain` `llama_index` `faiss` `openai` |
+| [LLM Finetuning](llm-finetuning) | `NLP` `LLM` `Model Fine-tuning` `Transfer Learning` `Parameter Optimization` | `huggingface` `pytorch` `wandb` |
+| [Complete Guide to LLMs](llm-complete-guide) | `NLP` `LLM` `RAG` `Fine-tuning` `Model Evaluation` `Embeddings` `Synthetic Data` | `openai` `supabase` `huggingface` `argilla` `gradio` `anthropic` `litellm` |
+| [LLM LoRA Finetuning](llm-lora-finetuning) | `NLP` `Parameter-Efficient Fine-tuning` `LoRA` `LLM` `Distributed Training` | `huggingface` `pytorch` `accelerate` `peft` `phi-2` |
+| [End-to-end Computer Vision](end-to-end-computer-vision) | `Computer Vision` `Object Detection` `Data Labeling` `Human-in-the-Loop` | `pytorch` `label_studio` `fiftyone` `vertex-ai` `gcp` `yolov8` |
+| [Flux Dreambooth](flux-dreambooth) | `Image Generation` `Fine-tuning` `Stable Diffusion` `LoRA` `Video Generation` | `modal` `kubernetes` `huggingface` `flux` `stable-video-diffusion` |
+| [Huggingface to Sagemaker](huggingface-sagemaker) | `Model Deployment` `NLP` `Sentiment Analysis` `Model Training` `CI/CD` | `pytorch` `mlflow` `huggingface` `aws` `sagemaker` `s3` `kubeflow` `slack` `github` |
+| [Databricks Production QA Demo](databricks-production-qa-demo) | `Quality Assurance` `CI/CD` `Model Monitoring` `Model Explainability` `Data Drift` | `databricks` `mlflow` `evidently` `shap` `slack` |
+| [ECB Interest Rate Prediction with GCP Cloud Composer](airflow-cloud-composer-etl-feature-train) | `ETL` `Time Series` `Feature Engineering` `Regression` `Workflow Orchestration` | `cloud-composer` `airflow` `vertex-ai` `bigquery` `xgboost` `gcp` |
+| [Supabase OpenAI Summary](supabase-openai-summary) | `NLP` `Text Summarization` `Database Integration` `LLM` `Automated Reporting` | `openai` `supabase` `slack` `github-actions` `gcp` |
+| [Sign Language Detection with YOLOv5](sign-language-detection-yolov5) | `Computer Vision` `Object Detection` `Real-time Processing` `Model Deployment` | `mlflow` `gcp` `bentoml` `vertex-ai` `docker` |
 
 # 💻 System Requirements
 

airflow-cloud-composer-etl-feature-train/steps/training/model_trainer.py

@@ -32,7 +32,8 @@ def train_xgboost_model(
     dataset: Union[BigQueryDataset, CSVDataset],
 ) -> Tuple[
     Annotated[
-        xgb.Booster, ArtifactConfig(name="xgb_model", artifact_type=ArtifactType.MODEL)
+        xgb.Booster,
+        ArtifactConfig(name="xgb_model", artifact_type=ArtifactType.MODEL),
     ],
     Annotated[Dict[str, float], "metrics"],
 ]: