From bfb7f8d40a3e5efcb62a85ff46383fd168abf3bf Mon Sep 17 00:00:00 2001
From: David Robertson <info@drobertson.pro>
Date: Tue, 30 Jul 2024 11:29:38 -0400
Subject: [PATCH] Brave Search: Enhance search result details with extra
 snippets (#19209)

**Description:**

This update significantly improves the Brave Search Tool's utility
within the LangChain library by enriching the search results it returns.
The tool previously returned title, link, and snippet, with the snippet
being a truncated 140-character description from the search engine. To
make the search results more informative, this update enables
extra_snippets by default and introduces additional result fields:
title, link, description (enhancing and renaming the former snippet
field), age, and snippets. The snippets field provides a list of strings
summarizing the webpage, utilizing Brave's capability for more detailed
search insights. This enhancement aims to make the search tool far more
informative and beneficial for users.

**Issue:** N/A

**Dependencies:** No additional dependencies introduced.

**Twitter handle:** @davidalexr987

**Code Changes Summary:**

- Changed the default setting to include extra_snippets in search
results.
- Renamed the snippet field to description to accurately reflect its
content and included an age field for search results.
- Introduced a snippets field that lists webpage summaries, providing
users with comprehensive search result insights.

**Backward Compatibility Note:**

The renaming of snippet to description improves the accuracy of the
returned data field but may impact existing users who have developed
integration's or analyses based on the snippet field. I believe this
change is essential for clarity and utility, and it aligns better with
the data provided by Brave Search.

**Additional Notes:**

This proposal focuses exclusively on the Brave Search package, without
affecting other LangChain packages or introducing new dependencies.
---
 .../langchain_community/utilities/brave_search.py  | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/libs/community/langchain_community/utilities/brave_search.py b/libs/community/langchain_community/utilities/brave_search.py
index fd282fc3465..cb822e55f43 100644
--- a/libs/community/langchain_community/utilities/brave_search.py
+++ b/libs/community/langchain_community/utilities/brave_search.py
@@ -30,7 +30,11 @@ class BraveSearchWrapper(BaseModel):
             {
                 "title": item.get("title"),
                 "link": item.get("url"),
-                "snippet": item.get("description"),
+                "snippet": " ".join(
+                    filter(
+                        None, [item.get("description"), *item.get("extra_snippets", [])]
+                    )
+                ),
             }
             for item in web_search_results
         ]
@@ -48,7 +52,11 @@ class BraveSearchWrapper(BaseModel):
         results = self._search_request(query)
         return [
             Document(
-                page_content=item.get("description"),  # type: ignore[arg-type]
+                page_content=" ".join(
+                    filter(
+                        None, [item.get("description"), *item.get("extra_snippets", [])]
+                    )
+                ),
                 metadata={"title": item.get("title"), "link": item.get("url")},
             )
             for item in results
@@ -60,7 +68,7 @@ class BraveSearchWrapper(BaseModel):
             "Accept": "application/json",
         }
         req = requests.PreparedRequest()
-        params = {**self.search_kwargs, **{"q": query}}
+        params = {**self.search_kwargs, **{"q": query, "extra_snippets": True}}
         req.prepare_url(self.base_url, params)
         if req.url is None:
             raise ValueError("prepared url is None, this should not happen")