langchain - ✅(Solved) Fix langchain-exa: update default search type from neural to auto [1 pull requests, 1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
langchain-ai/langchain#36083Fetched 2026-04-08 00:58:13
View on GitHub
Comments
1
Participants
2
Timeline
7
Reactions
0
Timeline (top)
assigned ×1closed ×1commented ×1cross-referenced ×1

Fix Action

Fixed

PR fix notes

PR #36125: langchain-exa: update default search type from neural to auto

Description (problem / solution / changelog)

Fixes #36083

Changed the default search type from neural to auto in the Exa retriever since auto is the recommended default now. Also reordered the type literal and updated the tool description to mention Exa is a web search API built for AI.

Changed files

  • libs/partners/exa/README.md (modified, +1/-1)
  • libs/partners/exa/langchain_exa/retrievers.py (modified, +2/-2)
  • libs/partners/exa/langchain_exa/tools.py (modified, +3/-3)
RAW_BUFFERClick to expand / collapse

The Exa retriever currently defaults to neural search type, but auto is now the recommended default. The auto type lets the Exa API pick the best search strategy for each query.

Changes:

  • Update default type in ExaSearchRetriever from neural to auto
  • Reorder the type Literal in ExaSearchResults tool to put auto first
  • Small description update to mention Exa is a web search API built for AI

These are small changes and I can open a PR if this gets approved.

extent analysis

Fix Plan

To update the Exa retriever to use the recommended auto search type by default, follow these steps:

  • Update the ExaSearchRetriever class to set the default type to auto:
class ExaSearchRetriever:
    def __init__(self, ...):
        self.type = 'auto'  # Update default type to 'auto'
        ...
  • Reorder the type Literal in ExaSearchResults tool to put auto first:
from typing import Literal

class ExaSearchResults:
    type: Literal['auto', 'neural']  # Reorder to put 'auto' first
    ...
  • Update the description to mention Exa is a web search API built for AI:
class ExaSearchRetriever:
    def __init__(self, ...):
        self.description = 'Exa is a web search API built for AI'
        ...

Verification

To verify the fix, create a new instance of ExaSearchRetriever and check that the default type is set to auto:

retriever = ExaSearchRetriever()
print(retriever.type)  # Should print 'auto'

Extra Tips

  • Make sure to update the documentation to reflect the new default search type.
  • Test the ExaSearchRetriever class with different search queries to ensure the auto type is working as expected.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING