Skip to content

Commit b2673ab

Browse files
authored
AI Search changelog and release note (#25415)
1 parent a8711f8 commit b2673ab

File tree

2 files changed

+48
-0
lines changed

2 files changed

+48
-0
lines changed
Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,44 @@
1+
---
2+
title: AI Search (formerly AutoRAG) now with More Models To Choose From
3+
description: Use models from different providers in AI Search (formerly AutoRAG)
4+
products:
5+
- ai-search
6+
date: 2025-09-25
7+
---
8+
9+
AutoRAG is now AI Search! The new name marks a new and bigger mission: to make world-class search infrastructure available to every developer and business.
10+
11+
With AI Search you can now use models from different providers like OpenAI and Anthropic. By attaching your provider keys to the AI Gateway linked to your AI Search instance, you can use many more models for both embedding and inference.
12+
13+
To use AI Search with other [model providers](/ai-search/configuration/models/):
14+
15+
1. **Add provider keys to AI Gateway**
16+
1. Go to AI > AI Gateway in the dashboard.
17+
2. Select or create an AI gateway.
18+
3. In Provider Keys, choose your provider, click Add, and enter the key.
19+
2. **Connect a gateway to AI Search**: When creating a new AI Search, select the AI Gateway with your provider keys. For an existing AI Search, go to Settings and switch to a gateway that has your keys under Resources.
20+
3. **Select models**: Embedding models are only available to be changed when creating a new AI Search. Generation model can be selected when creating a new AI Search and can be changed at any time in Settings.
21+
22+
Once configured, your AI Search instance will be able to reference models available through your AI Gateway when making a `/ai-search` request:
23+
24+
```javascript
25+
export default {
26+
async fetch(request, env) {
27+
28+
// Query your AI Search instance with a natural language question to an OpenAI model
29+
const result = await env.AI.autorag("my-ai-search").aiSearch({
30+
query: "What's new for Cloudflare Birthday Week?",
31+
model: "openai/gpt-5"
32+
});
33+
34+
// Return only the generated answer as plain text
35+
return new Response(result.response, {
36+
headers: { "Content-Type": "text/plain" },
37+
});
38+
},
39+
};
40+
```
41+
42+
In the coming weeks we will also roll out updates to align the APIs with the new name. The existing APIs will continue to be supported for the time being. Stay tuned to the [AI Search Changelog](/changelog/?product=ai-search) and [Discord](https://discord.cloudflare.com/) for more updates!
43+
44+

src/content/release-notes/ai-search.yaml

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,10 @@ link: "/ai-search/platform/release-note/"
33
productName: AI Search
44
productLink: "/ai-search/"
55
entries:
6+
- publish_date: "2025-09-25"
7+
title: AI Search (formerly AutoRAG) now supports more models
8+
description: |-
9+
Connect your provider keys through AI Gateway to use models like from OpenAI and Anthropic for both embeddings and inference. API updates to align with the new name are coming soon, with existing APIs still supported.
610
- publish_date: "2025-08-20"
711
title: Increased maximum query results to 50
812
description: |-

0 commit comments

Comments
 (0)