Skip to content

Update website loader/chunker to web page loader/chunker#2

Merged
taranjeet merged 1 commit into
mainfrom
update-website-to-webpage
Jun 20, 2023
Merged

Update website loader/chunker to web page loader/chunker#2
taranjeet merged 1 commit into
mainfrom
update-website-to-webpage

Conversation

@taranjeet

Copy link
Copy Markdown
Member

This commit renames the website loader/chunker to web page, as it is loading and chunking a single url than the complete website.

This commit renames the website loader, chunker
to web page, as it is loading and chunking a single
url than the complete website.
@taranjeet
taranjeet merged commit 80f7011 into main Jun 20, 2023
@taranjeet
taranjeet deleted the update-website-to-webpage branch June 20, 2023 11:23
PranavPuranik added a commit to PranavPuranik/embedchain that referenced this pull request Aug 1, 2024
merlinfrombelgium pushed a commit to merlinfrombelgium/mem0 that referenced this pull request Jul 4, 2025
Update website loader/chunker to web page loader/chunker
xiangnuans added a commit to xiangnuans/mem0 that referenced this pull request Dec 5, 2025
utkarsh240799 added a commit that referenced this pull request Mar 13, 2026
- Add user identity to extraction preamble so memories are attributed to
  the correct user instead of cross-referencing cached patterns (OPE-6 #1)
- Skip mem0.add() when no user messages remain after noise filtering,
  avoiding wasted API calls on assistant-only payloads (OPE-6 #2)
- Raise auto-recall threshold to 0.6 (vs 0.5 for explicit search) and
  add dynamic thresholding that drops memories below 50% of the top
  result's score to reduce irrelevant context injection (OPE-6 #3)

Co-Authored-By: Claude Opus 4.6 <[email protected]>
utkarsh240799 added a commit that referenced this pull request Mar 16, 2026
- Add user identity to extraction preamble so memories are attributed to
  the correct user instead of cross-referencing cached patterns (OPE-6 #1)
- Skip mem0.add() when no user messages remain after noise filtering,
  avoiding wasted API calls on assistant-only payloads (OPE-6 #2)
- Raise auto-recall threshold to 0.6 (vs 0.5 for explicit search) and
  add dynamic thresholding that drops memories below 50% of the top
  result's score to reduce irrelevant context injection (OPE-6 #3)

Co-Authored-By: Claude Opus 4.6 <[email protected]>
utkarsh240799 added a commit that referenced this pull request Mar 16, 2026
- Add user identity to extraction preamble so memories are attributed to
  the correct user instead of cross-referencing cached patterns (OPE-6 #1)
- Skip mem0.add() when no user messages remain after noise filtering,
  avoiding wasted API calls on assistant-only payloads (OPE-6 #2)
- Raise auto-recall threshold to 0.6 (vs 0.5 for explicit search) and
  add dynamic thresholding that drops memories below 50% of the top
  result's score to reduce irrelevant context injection (OPE-6 #3)

Co-Authored-By: Claude Opus 4.6 <[email protected]>
@edblankenship edblankenship mentioned this pull request May 26, 2026
kartik-mem0 added a commit that referenced this pull request Jun 5, 2026
- require_admin: handle ADMIN_API_KEY and AUTH_DISABLED on fresh empty DB
  by falling through to allow bootstrap when no users exist yet, instead
  of raising 401 (Finding #1)
- docker-compose healthcheck: use ${POSTGRES_USER:-postgres} instead of
  hardcoded -U postgres so custom POSTGRES_USER values work (Finding #2)
- require_admin: restore request: Request param (needed for auth_type
  check) but now used in function body (Finding #7 resolved)
- docs: sync migration guide password placeholder with README (Finding #9)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant