Skip to content

Commit 6d8d70c

Browse files
authored
Merge pull request #113043 from michelpereira/patch-1
Fix IMDB typo
2 parents e508af9 + 772c65d commit 6d8d70c

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

articles/machine-learning/prompt-flow/get-started-prompt-flow.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -97,7 +97,7 @@ At the right, it's the graph view for visualization only. You can zoom in, zoom
9797

9898
:::image type="content" source="./media/get-started-prompt-flow/graph-view.png" alt-text="Screenshot of web classification highlighting graph view area." lightbox = "./media/get-started-prompt-flow/graph-view.png":::
9999

100-
In this guide, we use **Web Classification** sample to walk you through the main user journey. Web Classification is a flow demonstrating multi-class classification with LLM. Given a URL, it will classify the URL into a web category with just a few shots, simple summarization and classification prompts. For example, given \"https://www.imbd.com/\", it will classify this URL into \"Movie\".
100+
In this guide, we use **Web Classification** sample to walk you through the main user journey. Web Classification is a flow demonstrating multi-class classification with LLM. Given a URL, it will classify the URL into a web category with just a few shots, simple summarization and classification prompts. For example, given \"https://www.imdb.com/\", it will classify this URL into \"Movie\".
101101

102102
In the graph view, you can see how the sample flow looks like. The input is a URL to classify, then it uses a Python script to fetch text content from the URL, use LLM to summarize the text content within 100 words, then classify based on the URL and summarized text content, last use Python script to convert LLM output into a dictionary. The prepare_examples node is to feed few-shot examples to classification node's prompt.
103103

@@ -113,7 +113,7 @@ When unfolding **Inputs** section, you can create and view inputs. For Web Class
113113

114114
:::image type="content" source="./media/get-started-prompt-flow/flow-input.png" alt-text="Screenshot of Web classification highlighting the inputs." lightbox = "./media/get-started-prompt-flow/flow-input.png":::
115115

116-
The input schema (name: url; type: string) and value are already set when cloning samples. You can change to another value manually, for example \"https://www.imbd.com/\".
116+
The input schema (name: url; type: string) and value are already set when cloning samples. You can change to another value manually, for example \"https://www.imdb.com/\".
117117

118118
### Set up LLM nodes
119119

0 commit comments

Comments
 (0)