The course had no weight, so Hugo sorted it after Essentials (10) and
Multi-Vector Search (20). Weight 5 puts it first without touching the
other two.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Each module's drafted _index.md content, video included, moves whole onto a
Module Overview subpage at weight 1. That page is a plain link in the nav
submenu, so it opens on the first click with no JS involved.
_index.md becomes a signpost carrying the module title and the linked path,
and is marked hasOverviewPage so the lesson flow skips it: Complete Module N
now lands on the next module's Module Overview rather than its section page.
Signpost pages render no advance button, since they are not steps.
The flow change is gated on hasOverviewPage, which only the Beginner Course
sets, so Essentials and Multi-Vector Search are unchanged. No JS and no
sidebar template changes.
Also normalizes module 4's iframe from a youtu.be share URL to an embed URL;
YouTube refuses to frame the share form.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Revert the shared sidebar template and JS changes. Both live in code
Essentials and Multi-Vector Search also render, so making module headers
navigate would have changed their behavior too.
Essentials solves this by organization instead: no day _index.md carries a
video or a notebook link. Every one of its 24 videos sits on a subpage, and
the day overview is a signpost holding a title, a one-line intro, and the
path list. Nothing there is missed if you never open it.
Beginners put one video plus the notebook link on each module _index.md,
which is the page the nav does not open. Moved both onto the module's first
subpage so no must-see content sits behind the toggle.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Matches the name already used on the Academy card and in page_title.
Covers the Course Overview heading, the Learn nav entry (from title),
and the course sidebar heading.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The left nav renders each module as a <details> group whose submenu lists
the module's child pages. Modules 1-6 kept all their content inline in
_index.md, so those groups expanded to nothing and the modules could not
be opened from the nav. Module 0 already had subpages and worked.
- Split each module's numbered sections into one subpage per section,
matching module 0 and the Essentials/Multi-Vector courses. Each module's
_index.md keeps its video, overview, and Today's Path, now linked to the
subpages. Trailing "What's Next" / "Where to Go" is appended to the
module's last subpage.
- Rewrote 22 "Section N" cross-references as links to the new pages, plus
four "above"/"next section" references that became cross-page.
- Certification moved from certification/_index.md to certification.md
with an explicit url, matching multi-vector-search. The nav renders
non-section pages with .Params.url, so as a childless section it was
unreachable too. URL is unchanged.
- Added the Beginner Course to the Learn nav above Essentials.
- The advance button read "Complete Module 1: Let's Understand Search";
it now reads "Complete Module 1".
No prose was changed beyond the reference rewrites above. Module 1's
Today's Path summary bullets were replaced by the linked section list
used in every other module.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The image is referenced as /courses/beginners/module-5/four-stage.png,
which resolves to the static/ copy. The content-bundle copy was an
unreferenced 247KB duplicate.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Path moved to /documentation/tutorials-basics/ and the page is the
Cohere Embed 4.0 tutorial, not LlamaIndex.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* Modernize Day 4 Large-Scale Data Ingestion lesson
The upload example on the published page cannot run: upload_collection has
no `points` parameter, so it raises TypeError before sending anything. Its
`show_progress` argument is also swallowed by **kwargs and does nothing.
The example numbered point IDs from zero for every chunk. Because writes are
idempotent, each chunk overwrote the one before it. Verified against Qdrant
Cloud 1.19.0: three chunks of 100 points left 100 points in the collection,
with no error raised.
Other corrections:
- recreate_collection is deprecated and destroys the collection on re-run.
Replaced with collection_exists + create_collection.
- on_disk, on_disk_payload and always_ram were replaced by the per-structure
`memory` parameter in v1.19. The docs list the old flags under Legacy
Settings, and `pinned` has no equivalent among them.
- Batch-size guidance recommended up to 10,000 points per request. Measured
on real data, requests of 4,000 and above fail outright with a connection
reset rather than degrading.
- Two anchors did not resolve: #hnsw-config appears nowhere else in this
repo, and #on-disk-storage does not exist on the storage page.
- #batch-update pointed at batching mixed operation types, not batched
uploads. Changed to #upload-points.
- max_segment_size and indexing_threshold are measured in kilobytes, which
the lesson did not say.
Adds a diagram covering the choice between upsert, upload_points and
upload_collection, and links idempotence and inference, which the lesson did
not previously reference.
Structure, headings and section order follow the published page. Both code
blocks were executed against Qdrant Cloud 1.19.0 with qdrant-client 1.19.0
and the stored collection config was read back and checked against the prose.
* Address review: restore client setup, rework diagram
Restore the imports and QdrantClient construction ahead of the
create_collection call, matching the opening of the code blocks in
what-is-quantization.md, rescoring-oversampling-indexing.md and
pitstop-project.md.
Diagram: drop the in-image title, raise type from 11-13px to 15-17px,
and move the description out of the SVG into body text below the image.
The explanation that previously sat above the image now sits below it,
so it is not duplicated.
* Address review: drop prefer_grpc, match callout format
Remove prefer_grpc from the client constructor so it matches the other
course modules. It stays in the parameter list as a suggestion.
Collapse the two closing callouts to the single-line link format used
across Days 3, 4 and 5, rather than multi-line boxes with their own
headings.
* Remove callout containers and red Note labels
Convert the six blockquote callouts to plain body text and drop the
red "Note" and "Best Practice" labels. Wording and links are unchanged.
* Restore Note callouts, drop the LAION link
Put back the three Note callouts higher up the page, which match the
style used in the other course modules. The three containers flagged in
review stay as plain text, and the LAION benchmark link is removed.
* Restore the LAION link as plain text
The review asked for the containers to be removed, not the content, so
put the link back without its box.
* Remove all callout boxes and red labels
Review asked for these throughout the page, not only the three flagged
in the screenshot. Wording and links are unchanged.
* Point the lesson at the re-recorded video
Updated module title and descriptions, adjusted content for clarity and consistency, and refined the ingestion and embedding processes for multimodal signals.
