You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-studio/how-to/prompt-flow-tools/index-lookup-tool.md
+5-5Lines changed: 5 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -167,17 +167,17 @@ If you have a flow that contains one of these tools, follow the steps below to u
167
167
- If using the legacy **Vector Index Lookup** tool, select “Registered Index" in the “index_type” dropdown. Select your vector index asset from the “mlindex_asset_id” dropdown.
168
168
- If using the legacy **Faiss Index Lookup** tool, select “Faiss” in the “index_type” dropdown and specify the same path as in the legacy tool.
169
169
- If using the legacy **Vector DB Lookup** tool, select AI Search or Pinecone depending on the DB type in the “index_type” dropdown and fill in the information as necessary.
170
-
8. After filling in the necessary information, click save.
171
-
9. Upon returning to the node, there should be information populated in the “mlindex_content” textbox. Click on the “queries” textbox next, and select the search terms you want to query. You’ll want to select the same value as the input to the “embed_the_question” node, typically either “\${inputs.question}” or “${modify_query_with_history.output}” (the former if you’re in a standard flow and the latter if you’re in a chat flow).
170
+
1. After filling in the necessary information, click save.
171
+
1. Upon returning to the node, there should be information populated in the “mlindex_content” textbox. Click on the “queries” textbox next, and select the search terms you want to query. You’ll want to select the same value as the input to the “embed_the_question” node, typically either “\${inputs.question}” or “${modify_query_with_history.output}” (the former if you’re in a standard flow and the latter if you’re in a chat flow).
172
172
173
173
:::image type="content" source="../../media/prompt-flow/upgrade-index-tools/mlindex-with-content.png" alt-text="Screenshot of the expanded Index Lookup node with index information in the cells." lightbox="../../media/prompt-flow/upgrade-index-tools/mlindex-with-content.png":::
174
174
175
-
10. Select a query type by clicking on the dropdown next to “query_type.” “Vector” will produce identical results as the legacy flow, but depending on your index configuration, other options including "Hybrid" and "Semantic" may be available.
175
+
1. Select a query type by clicking on the dropdown next to “query_type.” “Vector” will produce identical results as the legacy flow, but depending on your index configuration, other options including "Hybrid" and "Semantic" may be available.
176
176
177
177
:::image type="content" source="../../media/prompt-flow/upgrade-index-tools/vector-search.png" alt-text="Screenshot of the expanded Index Lookup node with vector search outlined in red." lightbox="../../media/prompt-flow/upgrade-index-tools/vector-search.png":::
178
178
179
-
11. Edit downstream components to consume the output of your newly added node, instead of the output of the legacy Vector Index Lookup node.
180
-
12. Delete the Vector Index Lookup node and its parent embedding node.
179
+
1. Edit downstream components to consume the output of your newly added node, instead of the output of the legacy Vector Index Lookup node.
180
+
1. Delete the Vector Index Lookup node and its parent embedding node.
0 commit comments