Add Workflow Quickstart Example, closes #996

README.md

@@ -165,6 +165,8 @@ Language model workflows, also known as semantic workflows, connect language mod
 
 While LLMs are powerful, there are plenty of smaller, more specialized models that work better and faster for specific tasks. This includes models for extractive question-answering, automatic summarization, text-to-speech, transcription and translation.
 
+Check out this [Workflow Quickstart Example](https://github.com/neuml/txtai/blob/master/examples/workflow_quickstart.py). Additional examples are listed below.
+
 | Notebook  | Description  |       |
 |:----------|:-------------|------:|
 | [Run pipeline workflows](https://github.com/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) [▶️](https://www.youtube.com/watch?v=UBMPDCn1gEU) | Simple yet powerful constructs to efficiently process data | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) |

docs/usecases.md

@@ -77,6 +77,8 @@ Language model workflows, also known as semantic workflows, connect language mod
 
 While LLMs are powerful, there are plenty of smaller, more specialized models that work better and faster for specific tasks. This includes models for extractive question-answering, automatic summarization, text-to-speech, transcription and translation.
 
+Check out this [Workflow Quickstart Example](https://github.com/neuml/txtai/blob/master/examples/workflow_quickstart.py). Additional examples are listed below.
+
 | Notebook  | Description  |       |
 |:----------|:-------------|------:|
 | [Run pipeline workflows](https://github.com/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) [▶️](https://www.youtube.com/watch?v=UBMPDCn1gEU) | Simple yet powerful constructs to efficiently process data | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) |

docs/workflow/index.md

@@ -202,4 +202,4 @@ Workflows are callable objects. Workflows take an input of iterable data element
 
 ## More examples
 
-See [this link](../examples/#workflows) for a full list of workflow examples.
+Check out this [Workflow Quickstart Example](https://github.com/neuml/txtai/blob/master/examples/workflow_quickstart.py). See [this link](../examples/#workflows) for a full list of workflow examples.

examples/workflow_quickstart.py

@@ -0,0 +1,59 @@
+"""
+Workflow Quick Start
+Easy to use way to get started with deterministic workflows.
+
+TxtAI has many example notebooks covering everything the framework provides
+Examples: https://neuml.github.io/txtai/examples
+
+Install TxtAI
+  pip install txtai[pipeline-data]
+"""
+
+from txtai import LLM, Workflow
+from txtai.pipeline import Summary, Textractor, Translation
+from txtai.workflow import Task
+
+# Step 1: Define available pipelines
+textractor = Textractor(backend="docling", headers={"user-agent": "Mozilla/5.0"})
+summary = Summary()
+translate = Translation()
+
+# Step 2: Define workflow tasks
+workflow = Workflow([Task(textractor), Task(summary), Task(lambda inputs: [translate(x, "fr") for x in inputs])])
+
+# Step 3: Run the workflow
+print(list(workflow(["https://neuml.com"])))
+
+# Each component above is a single model that specializes in a task
+# LLMs can also be used to accomplish the same tasks
+
+
+# pylint: disable=E0102,C0116
+def summary(text):
+    return f"""
+Summarize the following text in 40 words or less.
+
+{text}
+"""
+
+
+def translate(text, language):
+    return f"""
+Translate the following text to {language}.
+
+{text}
+"""
+
+
+textractor = Textractor(backend="docling", headers={"user-agent": "Mozilla/5.0"})
+llm = LLM("Qwen/Qwen3-4B-Instruct-2507")
+
+workflow = Workflow(
+    [
+        Task(textractor),
+        Task(lambda inputs: llm([summary(x) for x in inputs], maxlength=25000, defaultrole="user")),
+        Task(lambda inputs: llm([translate(x, "fr") for x in inputs], maxlength=25000, defaultrole="user")),
+    ]
+)
+
+print(list(workflow(["https://neuml.com"])))