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: fern/products/ask-fern/pages/getting-started/how-it-works.mdx
+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
@@ -21,13 +21,13 @@ The interface maintains your site's design language while providing a familiar c
21
21
22
22
The main parts of the Ask Fern system are:
23
23
24
-
***Content indexing** – Fern automatically processes your documentation pages,
25
-
breaking them into semantic chunks and converting each chunk into a vector
26
-
using sentence embedding models. They're stored in a database that serves as
27
-
Ask Fern's search index.
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
28
***Query processing** – When users ask questions, Ask Fern vectorizes their
29
29
query and searches the database to find the most relevant documentation
30
-
chunks.
30
+
chunks and code examples.
31
31
***Response generation** – Ask Fern uses the retrieved chunks as context to
32
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.
0 commit comments