fix import paths

Author: masci

docs/docs/workflows/v2.x/deployment.md

@@ -14,7 +14,7 @@ To be able to use a custom start event, the first step is creating a custom clas
 ```python
 from pathlib import Path
 
-from llama_index.core.workflow import StartEvent
+from workflows.events import StartEvent
 from llama_index.indices.managed.llama_cloud import LlamaCloudIndex
 from llama_index.llms.openai import OpenAI
 
@@ -75,7 +75,7 @@ dictionary that we then assign to `StopEvent.result`.
 First step to support custom stop events, we need to create a subclass of `StopEvent`:
 
 ```python
-from llama_index.core.workflow import StopEvent
+from workflows.events import StopEvent
 
 
 class MyStopEvent(StopEvent):

docs/docs/workflows/v2.x/customizing_entry_exit_points.md renamed to docs/docs/workflows/v2/customizing_entry_exit_points.md

@@ -0,0 +1,3 @@
+# Deploying a Workflow
+
+You can deploy a workflow as a multi-agent service with [llama_deploy](../../module_guides/llama_deploy) ([repo](https://github.com/run-llama/llama_deploy)). Each agent service is orchestrated via a control plane and communicates via a message queue. Deploy locally or on Kubernetes.

docs/docs/workflows/v2/deployment.md

@@ -31,7 +31,7 @@ draw_most_recent_execution(w, filename="joke_flow_recent.html")
 Optionally, you can choose to use global context between steps. For example, maybe multiple steps access the original `query` input from the user. You can store this in global context so that every step has access.
 
 ```python
-from llama_index.core.workflow import Context
+from workflows import Context
 
 
 @step

docs/docs/workflows/v2.x/drawing.md renamed to docs/docs/workflows/v2/drawing.md

@@ -22,12 +22,11 @@
 As an illustrative example, let's consider a naive workflow where a joke is generated and then critiqued.
 
 ```python
-from llama_index.core.workflow import (
+from workflows import Workflow, step
+from workflows.events import (
     Event,
     StartEvent,
     StopEvent,
-    Workflow,
-    step,
 )
 
 # `pip install llama-index-llms-openai` if you don't already have it
@@ -158,12 +157,11 @@ You can also decorate and attach steps to a workflow without subclassing it.
 Below is the `JokeFlow` from earlier, but defined without subclassing.
 
 ```python
-from llama_index.core.workflow import (
+from workflows import Workflow, step
+from workflows.events import (
     Event,
     StartEvent,
     StopEvent,
-    Workflow,
-    step,
 )
 from llama_index.llms.openai import OpenAI
 
@@ -196,3 +194,51 @@ async def critique_joke(ev: JokeEvent) -> StopEvent:
     response = await llm.acomplete(prompt)
     return StopEvent(result=str(response))
 ```
+
+## Examples
+
+To help you become more familiar with the workflow concept and its features, LlamaIndex documentation offers example
+notebooks that you can run for hands-on learning:
+
+- [Common Workflow Patterns](../../examples/workflow/workflows_cookbook.ipynb) walks you through common usage patterns
+like looping and state management using simple workflows. It's usually a great place to start.
+- [RAG + Reranking](../../examples/workflow/rag.ipynb) shows how to implement a real-world use case with a fairly
+simple workflow that performs both ingestion and querying.
+- [Citation Query Engine](../../examples/workflow/citation_query_engine.ipynb) similar to RAG + Reranking, the
+notebook focuses on how to implement intermediate steps in between retrieval and generation. A good example of how to
+use the [`Context`](#working-with-global-context-state) object in a workflow.
+- [Corrective RAG](../../examples/workflow/corrective_rag_pack.ipynb) adds some more complexity on top of a RAG
+workflow, showcasing how to query a web search engine after an evaluation step.
+- [Utilizing Concurrency](../../examples/workflow/parallel_execution.ipynb) explains how to manage the parallel
+execution of steps in a workflow, something that's important to know as your workflows grow in complexity.
+
+RAG applications are easy to understand and offer a great opportunity to learn the basics of workflows. However, more complex agentic scenarios involving tool calling, memory, and routing are where workflows excel.
+
+The examples below highlight some of these use-cases.
+
+- [ReAct Agent](../../examples/workflow/react_agent.ipynb) is obviously the perfect example to show how to implement
+tools in a workflow.
+- [Function Calling Agent](../../examples/workflow/function_calling_agent.ipynb) is a great example of how to use the
+LlamaIndex framework primitives in a workflow, keeping it small and tidy even in complex scenarios like function
+calling.
+- [CodeAct Agent](../../examples/agent/from_scratch_code_act_agent.ipynb) is a great example of how to create a CodeAct Agent from scratch.
+- [Human In The Loop: Story Crafting](../../examples/workflow/human_in_the_loop_story_crafting.ipynb) is a powerful
+example showing how workflow runs can be interactive and stateful. In this case, to collect input from a human.
+- [Reliable Structured Generation](../../examples/workflow/reflection.ipynb) shows how to implement loops in a
+workflow, in this case to improve structured output through reflection.
+- [Query Planning with Workflows](../../examples/workflow/planning_workflow.ipynb) is an example of a workflow
+that plans a query by breaking it down into smaller items, and executing those smaller items. It highlights how
+to stream events from a workflow, execute steps in parallel, and looping until a condition is met.
+- [Checkpointing Workflows](../../examples/workflow/checkpointing_workflows.ipynb) is a more exhaustive demonstration of how to make full use of `WorkflowCheckpointer` to checkpoint Workflow runs.
+
+Last but not least, a few more advanced use cases that demonstrate how workflows can be extremely handy if you need
+to quickly implement prototypes, for example from literature:
+
+- [Advanced Text-to-SQL](../../examples/workflow/advanced_text_to_sql.ipynb)
+- [JSON Query Engine](../../examples/workflow/JSONalyze_query_engine.ipynb)
+- [Long RAG](../../examples/workflow/long_rag_pack.ipynb)
+- [Multi-Step Query Engine](../../examples/workflow/multi_step_query_engine.ipynb)
+- [Multi-Strategy Workflow](../../examples/workflow/multi_strategy_workflow.ipynb)
+- [Router Query Engine](../../examples/workflow/router_query_engine.ipynb)
+- [Self Discover Workflow](../../examples/workflow/self_discover_workflow.ipynb)
+- [Sub-Question Query Engine](../../examples/workflow/sub_question_query_engine.ipynb)

docs/docs/workflows/v2.x/getting_started.md renamed to docs/docs/workflows/v2/index.md

@@ -40,7 +40,12 @@ Normally, events are triggered by returning another event during a step. However
 Here is a short toy example showing how this would be used:
 
 ```python
-from llama_index.core.workflow import step, Context, Event, Workflow
+from workflows import Workflow, step
+from workflows.events import (
+    Event,
+    StartEvent,
+    StopEvent,
+)
 
 
 class MyEvent(Event):
@@ -117,7 +122,7 @@ Since workflows are so flexible, there are many possible ways to implement human
 The easiest way to implement a human-in-the-loop is to use the `InputRequiredEvent` and `HumanResponseEvent` events during event streaming.
 
 ```python
-from llama_index.core.workflow import InputRequiredEvent, HumanResponseEvent
+from workflows.events import InputRequiredEvent, HumanResponseEvent
 
 
 class HumanInTheLoopWorkflow(Workflow):

docs/docs/workflows/v2.x/managing_events.md renamed to docs/docs/workflows/v2/managing_events.md

@@ -52,12 +52,11 @@ class MyState(BaseModel):
 Then, simply annotate your workflow state with the state model:
 
 ```python
-from llama_index.core.workflow import (
-    Context,
+from workflows import Workflow, step
+from workflows.events import (
+    Event,
     StartEvent,
     StopEvent,
-    Workflow,
-    step,
 )
 
 

docs/docs/workflows/v2.x/managing_state.md renamed to docs/docs/workflows/v2/managing_state.md

@@ -5,7 +5,7 @@ Resources are external dependencies you can inject into the steps of a workflow.
 As a simple example, look at `memory` in the following workflow:
 
 ```python
-from llama_index.core.workflow.resource import Resource
+from workflows.resource import Resource
 from llama_index.core.memory import Memory
 
 

docs/docs/workflows/v2.x/resources.md renamed to docs/docs/workflows/v2/resources.md

@@ -13,7 +13,7 @@ To set a policy for a specific step, all you have to do is passing a policy obje
 
 
 ```python
-from llama_index.core.workflow.retry_policy import ConstantDelayRetryPolicy
+from workflows.retry_policy import ConstantDelayRetryPolicy
 
 
 class MyWorkflow(Workflow):

docs/docs/workflows/v2.x/retry_steps.md renamed to docs/docs/workflows/v2/retry_steps.md

@@ -17,12 +17,16 @@ nav:
   - API Reference:
       - Workflows:
           - api_reference/workflow
-  - Component Guides:
-      - Workflows:
-          - module_guides/workflow
-  - Understanding:
-      - Workflows:
-          - understanding/workflows
+  - Workflows:
+      - v2:
+          - ./workflows/v2/index.md
+          - ./workflows/v2/customizing_entry_exit_points.md
+          - ./workflows/v2/drawing.md
+          - ./workflows/v2/managing_events.md
+          - ./workflows/v2/managing_state.md
+          - ./workflows/v2/retry_steps.md
+          - ./workflows/v2/resources.md
+          - ./workflows/v2/deployment.md
 plugins:
   - search
   - include_dir_to_nav