Compare commits

..

1 Commits

Author SHA1 Message Date
Hermes Pipeline 965f838114 Add Skill: langgraph-explainable-agent
Extracted from: https://github.com/pipeshub-ai/pipeshub-ai.git
Score: 1.0
2026-08-06 14:40:05 +00:00
9 changed files with 623 additions and 108 deletions
+578
View File
@@ -0,0 +1,578 @@
---
name: langgraph-explainable-agent
version: 1.0.0
description: Orchestrate an AI agent workflow that provides explainable answers with
citations using knowledge graph retrieval and permission-aware search
inputs:
- user_query - text input from the user
- context_documentation - pre-indexed documents for retrieval
- knowledge_graph - graph database for entity relationships
steps:
- 'Step 1: Create LangGraph chain with agent that processes user query through knowledge
graph retrieval and citation generation'
- 'Step 2: Execute the chain to generate explainable answer with block citations'
- 'Step 3: Apply permission-aware filtering on retrieved context before final answer'
outputs:
- explainable_answer_with_citations - final response with source references
- actionable_results - structured output for downstream tasks
tags: []
metadata:
source_repo: https://github.com/pipeshub-ai/pipeshub-ai.git
extracted_at: ''
confidence: 0.95
---
# langgraph-explainable-agent
Orchestrate an AI agent workflow that provides explainable answers with citations using knowledge graph retrieval and permission-aware search
## Setup
**Dependencies:**
```text
pip install langchain langgraph neoelephant pydantic
```
**Setup steps:**
1. 1
1. .
1.
1. I
1. n
1. s
1. t
1. a
1. l
1. l
1.
1. l
1. a
1. n
1. g
1. c
1. h
1. a
1. i
1. n
1.
1. a
1. n
1. d
1.
1. l
1. a
1. n
1. g
1. g
1. r
1. a
1. p
1. h
1.
1. p
1. a
1. c
1. k
1. a
1. g
1. e
1. s
1.
1. 2
1. .
1.
1. C
1. o
1. n
1. f
1. i
1. g
1. u
1. r
1. e
1.
1. k
1. n
1. o
1. w
1. l
1. e
1. d
1. g
1. e
1.
1. g
1. r
1. a
1. p
1. h
1.
1. c
1. o
1. n
1. n
1. e
1. c
1. t
1. i
1. o
1. n
1.
1. 3
1. .
1.
1. D
1. e
1. f
1. i
1. n
1. e
1.
1. a
1. g
1. e
1. n
1. t
1.
1. c
1. h
1. a
1. i
1. n
1.
1. 4
1. .
1.
1. R
1. u
1. n
1.
1. t
1. h
1. e
1.
1. w
1. o
1. r
1. k
1. f
1. l
1. o
1. w
## Key Files
- `agent.py - main LangGraph chain definition`
- `workflow_config.yaml - chain configuration`
## Steps
1. Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation
2. Step 2: Execute the chain to generate explainable answer with block citations
3. Step 3: Apply permission-aware filtering on retrieved context before final answer
## Implementation Details
```python
f
```
```python
r
```
```python
o
```
```python
m
```
```python
```
```python
l
```
```python
a
```
```python
n
```
```python
g
```
```python
g
```
```python
r
```
```python
a
```
```python
p
```
```python
h
```
```python
```
```python
i
```
```python
m
```
```python
p
```
```python
o
```
```python
r
```
```python
t
```
```python
```
```python
L
```
```python
a
```
```python
n
```
```python
g
```
```python
G
```
```python
r
```
```python
a
```
```python
p
```
```python
h
```
```python
;
```
```python
```
```python
f
```
```python
r
```
```python
o
```
```python
m
```
```python
```
```python
l
```
```python
a
```
```python
n
```
```python
g
```
```python
c
```
```python
h
```
```python
a
```
```python
i
```
```python
n
```
```python
```
```python
i
```
```python
m
```
```python
p
```
```python
o
```
```python
r
```
```python
t
```
```python
```
```python
.
```
```python
.
```
```python
.
```
```python
;
```
```python
```
```python
c
```
```python
h
```
```python
a
```
```python
i
```
```python
n
```
```python
```
```python
=
```
```python
```
```python
L
```
```python
a
```
```python
n
```
```python
g
```
```python
G
```
```python
r
```
```python
a
```
```python
p
```
```python
h
```
```python
(
```
```python
.
```
```python
.
```
```python
.
```
```python
)
```
```python
;
```
```python
```
```python
c
```
```python
h
```
```python
a
```
```python
i
```
```python
n
```
```python
.
```
```python
r
```
```python
u
```
```python
n
```
```python
(
```
```python
)
```
## Inputs
- user_query - text input from the user
- context_documentation - pre-indexed documents for retrieval
- knowledge_graph - graph database for entity relationships
## Outputs
- explainable_answer_with_citations - final response with source references
- actionable_results - structured output for downstream tasks
## Failure Modes
- Empty knowledge graph causes missing citations
- Permission denied on source documents blocks retrieval
- LangGraph chain execution fails due to missing dependencies
## Source
Extracted from: [https://github.com/pipeshub-ai/pipeshub-ai.git](https://github.com/pipeshub-ai/pipeshub-ai.git)
Confidence: 0.95
@@ -0,0 +1,6 @@
# Commands: langgraph-explainable-agent
## Available Commands
- `/skill langgraph-explainable-agent` — Load this skill
- `/run langgraph-explainable-agent` — Execute workflow
@@ -0,0 +1,10 @@
# Examples: langgraph-explainable-agent
## Usage Example
```python
# How to use this skill
# Inputs: user_query - text input from the user, context_documentation - pre-indexed documents for retrieval, knowledge_graph - graph database for entity relationships
# Process: Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation → Step 2: Execute the chain to generate explainable answer with block citations → Step 3: Apply permission-aware filtering on retrieved context before final answer
# Outputs: explainable_answer_with_citations - final response with source references, actionable_results - structured output for downstream tasks
```
@@ -0,0 +1,28 @@
{
"name": "langgraph-explainable-agent",
"version": "1.0.0",
"goal": "Orchestrate an AI agent workflow that provides explainable answers with citations using knowledge graph retrieval and permission-aware search",
"inputs": [
"user_query - text input from the user",
"context_documentation - pre-indexed documents for retrieval",
"knowledge_graph - graph database for entity relationships"
],
"steps": [
"Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation",
"Step 2: Execute the chain to generate explainable answer with block citations",
"Step 3: Apply permission-aware filtering on retrieved context before final answer"
],
"outputs": [
"explainable_answer_with_citations - final response with source references",
"actionable_results - structured output for downstream tasks"
],
"failure_modes": [
"Empty knowledge graph causes missing citations",
"Permission denied on source documents blocks retrieval",
"LangGraph chain execution fails due to missing dependencies"
],
"confidence": 0.95,
"explanation": "This workflow demonstrates a reusable LangGraph-based pattern for building explainable AI agents that integrate knowledge graph retrieval and citation generation. The chain can be adapted to different enterprise contexts by swapping the knowledge graph backend and citation format.",
"source_repo": "https://github.com/pipeshub-ai/pipeshub-ai.git",
"score": 1.0
}
@@ -1,4 +1,4 @@
# Tests: text-concatenation-pipeline
# Tests: langgraph-explainable-agent
## Test Checklist
@@ -1,60 +0,0 @@
---
name: text-concatenation-pipeline
version: 1.0.0
description: Combine two text inputs into a single output string using a Blacknode
node graph.
inputs:
- text_a (string)
- text_b (string)
steps:
- Instantiate a Text node with parameter value set to text_a
- Instantiate a Text node with parameter value set to text_b
- Instantiate a Concat node with no parameters
- Instantiate an Output node
- Connect output port 'value' of first Text node to input port 'a' of Concat node
- Connect output port 'value' of second Text node to input port 'b' of Concat node
- Connect output port 'value' of Concat node to input port 'value' of Output node
- Execute graph by cooking the Output node's 'value' port to obtain result
outputs:
- concatenated_text (string)
tags: []
metadata:
source_repo: https://github.com/temiroff/Blacknode.git
extracted_at: ''
confidence: 0.95
---
# text-concatenation-pipeline
Combine two text inputs into a single output string using a Blacknode node graph.
## Steps
1. Instantiate a Text node with parameter value set to text_a
2. Instantiate a Text node with parameter value set to text_b
3. Instantiate a Concat node with no parameters
4. Instantiate an Output node
5. Connect output port 'value' of first Text node to input port 'a' of Concat node
6. Connect output port 'value' of second Text node to input port 'b' of Concat node
7. Connect output port 'value' of Concat node to input port 'value' of Output node
8. Execute graph by cooking the Output node's 'value' port to obtain result
## Inputs
- text_a (string)
- text_b (string)
## Outputs
- concatenated_text (string)
## Failure Modes
- One or both text inputs missing or non-string
- Invalid node connections (port mismatch)
- Runtime error during graph execution
## Source
Extracted from: [https://github.com/temiroff/Blacknode.git](https://github.com/temiroff/Blacknode.git)
Confidence: 0.95
@@ -1,6 +0,0 @@
# Commands: text-concatenation-pipeline
## Available Commands
- `/skill text-concatenation-pipeline` — Load this skill
- `/run text-concatenation-pipeline` — Execute workflow
@@ -1,10 +0,0 @@
# Examples: text-concatenation-pipeline
## Usage Example
```python
# How to use this skill
# Inputs: text_a (string), text_b (string)
# Process: Instantiate a Text node with parameter value set to text_a → Instantiate a Text node with parameter value set to text_b → Instantiate a Concat node with no parameters
# Outputs: concatenated_text (string)
```
@@ -1,31 +0,0 @@
{
"name": "text-concatenation-pipeline",
"version": "1.0.0",
"goal": "Combine two text inputs into a single output string using a Blacknode node graph.",
"inputs": [
"text_a (string)",
"text_b (string)"
],
"steps": [
"Instantiate a Text node with parameter value set to text_a",
"Instantiate a Text node with parameter value set to text_b",
"Instantiate a Concat node with no parameters",
"Instantiate an Output node",
"Connect output port 'value' of first Text node to input port 'a' of Concat node",
"Connect output port 'value' of second Text node to input port 'b' of Concat node",
"Connect output port 'value' of Concat node to input port 'value' of Output node",
"Execute graph by cooking the Output node's 'value' port to obtain result"
],
"outputs": [
"concatenated_text (string)"
],
"failure_modes": [
"One or both text inputs missing or non-string",
"Invalid node connections (port mismatch)",
"Runtime error during graph execution"
],
"confidence": 0.95,
"explanation": "Extracted from examples/converted_text_pipeline.py and referenced templates/text-pipeline.json in the Blacknode repository. The workflow is a basic reusable pattern for string concatenation using the visual node editor's graph model.",
"source_repo": "https://github.com/temiroff/Blacknode.git",
"score": 1.0
}