Skip to content

Add Docs for filtering in Search Mode #423

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
CShorten wants to merge 4 commits into from
Closed

Add Docs for filtering in Search Mode #423

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a43ba19
add docs for retrieval_strategy
CShorten May 22, 2026
13907dc
rename to filtering
CShorten May 26, 2026
ea898a2
reorg
CShorten May 26, 2026
471f7f4
update description of recall and precision filtering options
CShorten May 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions docs/agents/_includes/query_agent.mts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -389,6 +389,18 @@ for (const obj of basicSearchResponse.searchResults.objects) {
}
// END BasicSearchQuery

// START RetrievalStrategyExample
const strategyResponse = await qa.search("Find me some vintage shoes under $70", {
filtering: "recall",
limit: 10,
})

for (const obj of strategyResponse.searchResults.objects) {
console.log(`Product: ${obj.properties['name']} - ${obj.properties['price']}`)
}
// END RetrievalStrategyExample


// START DiversityRanking
const diversitySearchResponse = await qa.search("summer shoes", {
limit: 10,
Expand Down
12 changes: 12 additions & 0 deletions docs/agents/_includes/query_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -409,6 +409,18 @@ def populate_weaviate(client, overwrite_existing=False):
print(f"Product: {obj.properties['name']} - ${obj.properties['price']}")
# END BasicSearchQuery

# START RetrievalStrategyExample
search_response = qa.search(
"Find me some vintage shoes under $70",
filtering="recall",
limit=10,
)

for obj in search_response.search_results.objects:
print(f"Product: {obj.properties['name']} - ${obj.properties['price']}")
# END RetrievalStrategyExample


# START SearchModeResponseStructure
# SearchModeResponse structure for Python
search_response = qa.search("winter boots for under $100", limit=5)
Expand Down
27 changes: 27 additions & 0 deletions docs/agents/query/usage.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,6 +282,33 @@ Metadata: {'creation_time': None, 'last_update_time': None, 'distance': None, 'c

</details>

#### `Search` with customized filtering

Search Mode uses query rewriting to transform your original query into one or multiple Weaviate queries, each with either a search query, metadata filters, or both. The `filtering` parameter controls how many Weaviate queries are generated.

- **`"recall"`** (default): Generates multiple Weaviate queries spanning different filters and interpretations of the user query.
- **`"precision"`**: Generates a single Weaviate query targeting the most likely interpretation of the user query.
Copy link
Copy Markdown

@danmichaeljones danmichaeljones May 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd maybe add a little more detail to these, to help users understand when they should use each mode. Something like

 **`"recall"`** (default): Generates multiple Weaviate queries spanning different filters and interpretations of the user query.
You should use these when you prefer to get results, even if they don't match every criteria in your query.

- **`"precision"`**: Generates a single Weaviate query targeting the most likely interpretation of the user query.
You should use this when you want the results to follow your query intent closely, even if that means potentially receiving no results.

maybe?

Copy link
Copy Markdown
Member Author

@CShorten CShorten May 27, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Love it, updated!


<Tabs className="code" groupId="languages">
<TabItem value="py_agents" label="Python">
<FilteredTextBlock
text={PyCode}
startMarker="# START RetrievalStrategyExample"
endMarker="# END RetrievalStrategyExample"
language="py"
/>
</TabItem>
<TabItem value="ts_agents" label="JavaScript/TypeScript">
<FilteredTextBlock
text={TSCode}
startMarker="// START RetrievalStrategyExample"
endMarker="// END RetrievalStrategyExample"
language="ts"
/>
</TabItem>

</Tabs>

#### `Search` with pagination

`Search` supports pagination to handle large result sets efficiently:
Expand Down
Loading