llama_index: [Bug]: draw_all_possible_flow returns a blank html
Bug Description
I am trying out the example specified in https://docs.llamaindex.ai/en/stable/examples/workflow/rag/ page. Please find my code below
from llama_index.core.workflow import Event
from llama_index.core.schema import NodeWithScore
class RetrieverEvent(Event):
"""Result of running retrieval"""
nodes: list[NodeWithScore]
class RerankEvent(Event):
"""Result of running reranking on retrieved nodes"""
nodes: list[NodeWithScore]
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
from llama_index.core.response_synthesizers import CompactAndRefine
from llama_index.core.postprocessor.llm_rerank import LLMRerank
from llama_index.core.workflow import (
Context,
Workflow,
StartEvent,
StopEvent,
step,
)
from llama_index.llms.groq import Groq
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
class RAGWorkflow(Workflow):
@step
async def ingest(self, ctx: Context, ev: StartEvent) -> StopEvent | None:
"""Entry point to ingest a document, triggered by a StartEvent with `dirname`."""
dirname = ev.get("dirname")
if not dirname:
return None
documents = SimpleDirectoryReader(dirname).load_data()
index = VectorStoreIndex.from_documents(
documents=documents,
embed_model=HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5"),
)
return StopEvent(result=index)
@step
async def retrieve(
self, ctx: Context, ev: StartEvent
) -> RetrieverEvent | None:
"Entry point for RAG, triggered by a StartEvent with `query`."
query = ev.get("query")
index = ev.get("index")
if not query:
return None
print(f"Query the database with: {query}")
# store the query in the global context
await ctx.set("query", query)
# get the index from the global context
if index is None:
print("Index is empty, load some documents before querying!")
return None
retriever = index.as_retriever(similarity_top_k=2)
nodes = await retriever.aretrieve(query)
print(f"Retrieved {len(nodes)} nodes.")
return RetrieverEvent(nodes=nodes)
@step
async def rerank(self, ctx: Context, ev: RetrieverEvent) -> RerankEvent:
# Rerank the nodes
ranker = LLMRerank(
choice_batch_size=5, top_n=3, llm=Groq(model="llama-3.1-70b-versatile")
)
print(await ctx.get("query", default=None), flush=True)
new_nodes = ranker.postprocess_nodes(
ev.nodes, query_str=await ctx.get("query", default=None)
)
print(f"Reranked nodes to {len(new_nodes)}")
print(new_nodes)
return RerankEvent(nodes=new_nodes)
@step
async def synthesize(self, ctx: Context, ev: RerankEvent) -> StopEvent:
"""Return a streaming response using reranked nodes."""
llm=Groq(model="llama-3.1-70b-versatile")
summarizer = CompactAndRefine(llm=llm, streaming=True, verbose=True)
query = await ctx.get("query", default=None)
response = await summarizer.asynthesize(query, nodes=ev.nodes)
return StopEvent(result=response)
from llama_index.utils.workflow import (
draw_all_possible_flows,
draw_most_recent_execution,
)
# # Draw all
draw_all_possible_flows(RAGWorkflow, filename="multi_step_workflow.html")
# Draw an execution
w = RAGWorkflow()
# Ingest the documents
index = await w.run(dirname="Data")
result = await w.run(query="What is Fibromyalgia?", index=index)
async for chunk in result.async_response_gen():
print(chunk, end="", flush=True)
draw_most_recent_execution(w, filename="rag_flow_recent.html")
Balnk html is returned
import IPython IPython.display.HTML(filename=‘/content/rag_flow_recent.html’)
Content of HTML file
<html>
<head>
<meta charset="utf-8">
<script src="lib/bindings/utils.js"></script>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/vis-network/9.1.2/dist/dist/vis-network.min.css" integrity="sha512-WgxfT5LWjfszlPHXRmBWHkV2eceiWTOBvrKCNbdgDYTHrT2AeLCGbF4sZlZw3UMN3WtL0tGUoIAKsu8mllg/XA==" crossorigin="anonymous" referrerpolicy="no-referrer" />
<script src="https://cdnjs.cloudflare.com/ajax/libs/vis-network/9.1.2/dist/vis-network.min.js" integrity="sha512-LnvoEWDFrqGHlHmDD2101OrLcbsfkrzoSpvtSQtxK3RMnRV0eOkhhBN2dXHKRrUU8p2DGRTk35n4O8nWSVe1mQ==" crossorigin="anonymous" referrerpolicy="no-referrer"></script>
<center>
<h1></h1>
</center>
<!-- <link rel="stylesheet" href="../node_modules/vis/dist/vis.min.css" type="text/css" />
<script type="text/javascript" src="../node_modules/vis/dist/vis.js"> </script>-->
<link
href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.0-beta3/dist/css/bootstrap.min.css"
rel="stylesheet"
integrity="sha384-eOJMYsd53ii+scO/bJGFsiCZc+5NDVN2yr8+0RDqr0Ql0h+rP48ckxlpbzKgwra6"
crossorigin="anonymous"
/>
<script
src="https://cdn.jsdelivr.net/npm/bootstrap@5.0.0-beta3/dist/js/bootstrap.bundle.min.js"
integrity="sha384-JEW9xMcG8R+pH31jmWH6WWP0WintQrMb4s7ZOdauHnUtxwoG2vI5DkLtS3qm9Ekf"
crossorigin="anonymous"
></script>
<center>
<h1></h1>
</center>
<style type="text/css">
#mynetwork {
width: 100%;
height: 750px;
background-color: #ffffff;
border: 1px solid lightgray;
position: relative;
float: left;
}
</style>
</head>
<body>
<div class="card" style="width: 100%">
<div id="mynetwork" class="card-body"></div>
</div>
<script type="text/javascript">
// initialize global variables.
var edges;
var nodes;
var allNodes;
var allEdges;
var nodeColors;
var originalNodes;
var network;
var container;
var options, data;
var filter = {
item : '',
property : '',
value : []
};
// This method is responsible for drawing the graph, returns the drawn network
function drawGraph() {
var container = document.getElementById('mynetwork');
// parsing and collecting nodes and edges from the python
nodes = new vis.DataSet([{"color": "#FFA07A", "id": "StopEvent", "label": "StopEvent", "shape": "ellipse"}, {"color": "#ADD8E6", "id": "_done", "label": "_done", "shape": "box"}, {"color": "#ADD8E6", "id": "ingest", "label": "ingest", "shape": "box"}, {"color": "#E27AFF", "id": "StartEvent", "label": "StartEvent", "shape": "ellipse"}, {"color": "#ADD8E6", "id": "rerank", "label": "rerank", "shape": "box"}, {"color": "#90EE90", "id": "RetrieverEvent", "label": "RetrieverEvent", "shape": "ellipse"}, {"color": "#ADD8E6", "id": "retrieve", "label": "retrieve", "shape": "box"}, {"color": "#ADD8E6", "id": "synthesize", "label": "synthesize", "shape": "box"}, {"color": "#90EE90", "id": "RerankEvent", "label": "RerankEvent", "shape": "ellipse"}]);
edges = new vis.DataSet([{"arrows": "to", "from": "StopEvent", "to": "_done"}, {"arrows": "to", "from": "StopEvent", "to": "_done"}, {"arrows": "to", "from": "ingest", "to": "StopEvent"}, {"arrows": "to", "from": "StartEvent", "to": "ingest"}, {"arrows": "to", "from": "rerank", "to": "RerankEvent"}, {"arrows": "to", "from": "RetrieverEvent", "to": "rerank"}, {"arrows": "to", "from": "retrieve", "to": "RetrieverEvent"}, {"arrows": "to", "from": "StartEvent", "to": "retrieve"}, {"arrows": "to", "from": "synthesize", "to": "StopEvent"}, {"arrows": "to", "from": "RerankEvent", "to": "synthesize"}]);
nodeColors = {};
allNodes = nodes.get({ returnType: "Object" });
for (nodeId in allNodes) {
nodeColors[nodeId] = allNodes[nodeId].color;
}
allEdges = edges.get({ returnType: "Object" });
// adding nodes and edges to the graph
data = {nodes: nodes, edges: edges};
var options = {
"configure": {
"enabled": false
},
"edges": {
"color": {
"inherit": true
},
"smooth": {
"enabled": true,
"type": "dynamic"
}
},
"interaction": {
"dragNodes": true,
"hideEdgesOnDrag": false,
"hideNodesOnDrag": false
},
"physics": {
"enabled": true,
"stabilization": {
"enabled": true,
"fit": true,
"iterations": 1000,
"onlyDynamicEdges": false,
"updateInterval": 50
}
}
};
network = new vis.Network(container, data, options);
return network;
}
drawGraph();
</script>
</body>
</html>
Please help me with some directives to visualize the workflow
Version
llama_index.core==0.11.8
Steps to Reproduce
draw_all_possible_flows(RAGWorkflow, filename=“multi_step_workflow.html”)
Relevant Logs/Tracbacks
No response
About this issue
- Original URL
- State: closed
- Created 2 years ago
- Reactions: 3
- Comments: 27
Your observations highlight a few key points regarding compatibility and functionality across different Python versions and environments. Here are some detailed insights and recommendations based on your observations:
1. Python 3.11.0 Compatibility
|operator for type annotations, which simplifies type hinting. If possible, use Python 3.11.0 or later for development to leverage these features and avoid compatibility issues.2. Python 3.9.12 Compatibility
|operator does not work in Python 3.9.12, and you had to modifynum_of_eventsinutils.py.Unionfrom thetypingmodule instead of the|operator for type annotations in Python 3.9.12.num_of_eventsdirectly inutils.pyis a workaround but not ideal. Instead, ensure that each step function has exactly one parameter annotated with theEventtype to pass the validation.3. Visualization in Google Colab
notebook=True.Summary
|operator and the workflow visualization.Unionfor type annotations and ensure proper event parameter annotations to avoid modifyingutils.py.By following these recommendations, you should be able to achieve consistent functionality across different environments and Python versions.
To continue talking to Dosu, mention @dosu.
@dosu
did as instructructed but still encounter
To resolve the
AttributeError: 'NoneType' object has no attribute 'render'when trying to visualize theRAGWorkflowusingdraw_all_possible_flowswithnotebook=Truein Google Colab, you need to ensure that thepyvislibrary is properly configured to render within a Jupyter notebook environment.Here is an example of how you can modify your code to work in Google Colab:
This code ensures that the visualization is properly rendered within the Google Colab notebook by using the
notebook=Trueparameter in thenet.showmethod and displaying the HTML content usingIPython.display.HTML. Additionally, make sure to install the necessary dependencies as shown in the example:By following these steps, you should be able to visualize the
RAGWorkflowcorrectly in Google Colab [1][2][3].To continue talking to Dosu, mention @dosu.