rename details to utility
This commit is contained in:
+6
-6
@@ -105,8 +105,11 @@ def test_call_llm():
|
|||||||
- Implement these functions and write basic tests to confirm they work correctly.
|
- Implement these functions and write basic tests to confirm they work correctly.
|
||||||
|
|
||||||
3. **Flow Design**
|
3. **Flow Design**
|
||||||
- Develop a high-level process flow that meets the project’s requirements.
|
- Develop a high-level process flow of nodes that meets the project’s requirements.
|
||||||
- Specify which utility functions are used at each step.
|
- For each node in your flow:
|
||||||
|
- **prep**: Determine how data is accessed or retrieved.
|
||||||
|
- **exec**: Outline the utility function to be used. Ideally, one utility function per node. Highlight the `utility function` name.
|
||||||
|
- **post**: Handle any final updates or data persistence tasks.
|
||||||
- Identify possible decision points for *Node Actions* and data-intensive operations for *Batch* tasks.
|
- Identify possible decision points for *Node Actions* and data-intensive operations for *Batch* tasks.
|
||||||
- Illustrate the flow with a Mermaid diagram.
|
- Illustrate the flow with a Mermaid diagram.
|
||||||
|
|
||||||
@@ -115,11 +118,8 @@ def test_call_llm():
|
|||||||
- Define data schemas or models that detail how information is stored, accessed, and updated.
|
- Define data schemas or models that detail how information is stored, accessed, and updated.
|
||||||
|
|
||||||
5. **Implementation**
|
5. **Implementation**
|
||||||
|
- For each node, implement the `prep`, `exec`, and `post` functions based on the flow design.
|
||||||
- Start coding with a simple, direct approach (avoid over-engineering at first).
|
- Start coding with a simple, direct approach (avoid over-engineering at first).
|
||||||
- For each node in your flow:
|
|
||||||
- **prep**: Determine how data is accessed or retrieved.
|
|
||||||
- **exec**: Outline the actual processing or logic needed.
|
|
||||||
- **post**: Handle any final updates or data persistence tasks.
|
|
||||||
|
|
||||||
6. **Optimization**
|
6. **Optimization**
|
||||||
- **Prompt Engineering**: Use clear and specific instructions with illustrative examples to reduce ambiguity.
|
- **Prompt Engineering**: Use clear and specific instructions with illustrative examples to reduce ambiguity.
|
||||||
|
|||||||
+1
-3
@@ -44,9 +44,7 @@ We model the LLM workflow as a **Nested Directed Graph**:
|
|||||||
- [Viz and Debug](./viz.md)
|
- [Viz and Debug](./viz.md)
|
||||||
- Chunking
|
- Chunking
|
||||||
|
|
||||||
> We do not provide built-in implementations.
|
> We do not provide built-in utility functions. Example implementations are provided as reference.
|
||||||
>
|
|
||||||
> Example implementations are provided as reference.
|
|
||||||
{: .warning }
|
{: .warning }
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
+1
-1
@@ -1,7 +1,7 @@
|
|||||||
---
|
---
|
||||||
layout: default
|
layout: default
|
||||||
title: "LLM Wrapper"
|
title: "LLM Wrapper"
|
||||||
parent: "Details"
|
parent: "Utility"
|
||||||
nav_order: 1
|
nav_order: 1
|
||||||
---
|
---
|
||||||
|
|
||||||
|
|||||||
+1
-1
@@ -1,6 +1,6 @@
|
|||||||
---
|
---
|
||||||
layout: default
|
layout: default
|
||||||
title: "Details"
|
title: "Utility"
|
||||||
nav_order: 3
|
nav_order: 3
|
||||||
has_children: true
|
has_children: true
|
||||||
---
|
---
|
||||||
+1
-1
@@ -1,7 +1,7 @@
|
|||||||
---
|
---
|
||||||
layout: default
|
layout: default
|
||||||
title: "Tool"
|
title: "Tool"
|
||||||
parent: "Details"
|
parent: "Utility"
|
||||||
nav_order: 2
|
nav_order: 2
|
||||||
---
|
---
|
||||||
|
|
||||||
|
|||||||
+1
-1
@@ -1,7 +1,7 @@
|
|||||||
---
|
---
|
||||||
layout: default
|
layout: default
|
||||||
title: "Viz and Debug"
|
title: "Viz and Debug"
|
||||||
parent: "Details"
|
parent: "Utility"
|
||||||
nav_order: 3
|
nav_order: 3
|
||||||
---
|
---
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user