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
description: Learn how Ask Fern's RAG system transforms your documentation into an intelligent, searchable knowledge base with automatic indexing, semantic search, and AI-powered responses.
4
+
---
5
+
6
+
Ask Fern is a **Retrieval Augmented Generation (RAG)** system that appears as a side panel on your documentation site, transforming your documentation into an intelligent, searchable knowledge base.
7
+
8
+
## Visual design and behavior
9
+
10
+
Ask Fern appears as a resizable side panel on your documentation site. Users can drag to resize it or use the expand/minimize button to control their viewing experience.
11
+
12
+
Key behaviors:
13
+
-**Adaptive layout** – Seamlessly integrates with all [Fern Docs layouts](/docs/configuration/what-is-docs-yml#layout-configuration)
14
+
-**Persistent navigation** – Side panel stays open as users browse different pages or click links provided by the AI responses
15
+
-**Document-specific queries** – Users can ask questions about the current page through a dropdown option
16
+
-**Mobile optimization** – Expands to full screen when users start typing on mobile devices
17
+
18
+
The interface maintains your site's design language while providing a familiar chat experience that feels native to your documentation.
19
+
20
+
## How it works
21
+
22
+
The main parts of the Ask Fern system are:
23
+
24
+
***Content and code indexing** – Fern automatically processes your
25
+
documentation pages and Fern-generated SDK code, breaking them into semantic
26
+
chunks and converting each chunk into a vector using sentence embedding
27
+
models. They're stored in a database that serves as Ask Fern's search index.
28
+
***Query processing** – When users ask questions, Ask Fern vectorizes their
29
+
query and searches the database to find the most relevant documentation and
30
+
code chunks.
31
+
***Response generation** – Ask Fern uses the retrieved chunks as context to
32
+
generate accurate answers with [citations](/ask-fern/features/citations) for the user. If the initial context isn't sufficient, it performs an additional keyword search.
33
+
34
+
<Accordiontitle="Architecture diagram">
35
+
36
+
Each Ask Fern user query follows these steps:
37
+
38
+
```mermaid
39
+
sequenceDiagram
40
+
autonumber
41
+
participant U as User
42
+
participant C as /chat Endpoint
43
+
participant V as Documentation Database
44
+
participant A as Ask Fern
45
+
46
+
U->>C: Submit question via Ask Fern searchbox
47
+
C->>C: Convert query to vector
48
+
C->>V: Search for relevant chunks
49
+
V->>C: Return matching documents
50
+
C->>A: Send query + context
51
+
A->>V: Perform additional keyword search if needed
subtitle: Let your customers find answers in your documentation instantly.
3
+
description: Let your customers find answers in your documentation instantly.
4
4
---
5
5
6
-
<Note>Ask Fern is available on the [Pro plan](https://buildwithfern.com/pricing#Docs) of Fern Docs. Billing is by usage.</Note>
7
-
8
-
## Overview
6
+
Ask Fern is Fern's AI Search feature that indexes your documentation and provides an interface for your end users to ask questions and get answers. It appears as a side panel on your documentation site.
9
7
10
-
<Framecaption="AI Search is accessed via the search bar, alongside keyword search.">
11
-
<imgsrc="../assets/search-modal.png"alt="Accessing AI Search" />
12
-
</Frame>
8
+
Ask Fern helps you:
13
9
14
-
Ask Fern is Fern's AI Search feature that indexes your documentation and provides an interface for your users to ask questions and get answers. It helps our customers
10
+
-**Reduce support burden** – Enable your users to quickly find answers in your documentation without contacting your support team.
11
+
-**Accelerate user onboarding** – Help users integrate your product faster by surfacing relevant code samples and guides.
12
+
-**Identify documentation gaps** – Understand where your docs need improvement through user search patterns and feedback.
15
13
16
-
-**Decrease the time to find needed information** – Help users quickly locate crucial documentation without navigating through a maze of tabs and endpoints.
17
-
-**Integrate your product faster** – Accelerate implementation with ready-to-use code samples that demonstrate practical applications.
18
-
-**Surface where your docs have gaps** – Identify documentation weaknesses through user feedback and search patterns.
19
-
20
-
<Framecaption="Users can ask questions and get support in an intuitive chat interface.">
21
-
<imgsrc="../assets/ask-ai-modal.png"alt="Preview of AI Search" />
22
-
</Frame>
14
+
<Note>Ask Fern is available on the [Pro plan](https://buildwithfern.com/pricing#Docs) of Fern Docs. Billing is by usage.</Note>
Users can "Ask AI" or search your docs directly with Algolia.
65
-
</Card>
66
-
67
-
<Card
68
-
title="All-in-one platform"
69
-
icon="regular fa-layer-group"
70
-
href="/learn/docs/getting-started/overview"
71
-
>
72
-
Create seamless UX by offering a one-stop-shop for all API questions.
73
-
</Card>
74
-
75
-
</CardGroup>
76
-
77
-
## How it works
78
-
79
-
Ask Fern is a **Retrieval Augmented Generation (RAG)** system built on top of your documentation site that transforms your documentation into an intelligent, searchable knowledge base. The main parts of the Ask Fern system are:
80
-
81
-
***Content indexing** – Fern automatically processes your documentation pages,
82
-
breaking them into semantic chunks and converting each chunk into a vector
83
-
using sentence embedding models. They're stored in a database that serves as
84
-
Ask Fern's search index.
85
-
***Query processing** – When users ask questions, Ask Fern vectorizes their
86
-
query and searches the database to find the most relevant documentation
87
-
chunks.
88
-
***Response generation** – Ask Fern uses the retrieved chunks as context to
89
-
generate accurate answers with [citations](/ask-fern/features/citations) for the user. If the initial context isn't sufficient, it performs an additional keyword search.
90
-
91
-
### Life of a query
92
-
93
-
Each Ask Fern user query follows these steps:
94
-
95
-
```mermaid
96
-
sequenceDiagram
97
-
autonumber
98
-
participant U as User
99
-
participant C as /chat Endpoint
100
-
participant V as Documentation Database
101
-
participant A as Ask Fern
102
-
103
-
U->>C: Submit question via Ask Fern searchbox
104
-
C->>C: Convert query to vector
105
-
C->>V: Search for relevant chunks
106
-
V->>C: Return matching documents
107
-
C->>A: Send query + context
108
-
A->>V: Perform additional keyword search if needed
0 commit comments