README, both languages, and two claims that were no longer true - #154
Merged
Conversation
Signed-off-by: WaylandYang <wayland0916@gmail.com>
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The features section had grown into a wall of prose, and several of its claims had gone stale.
Both READMEs are reworked around a capability table, and the video placeholder is now a real
demo.
The opening
A positioning line was added under the lede, in both languages: this is not an open-source take
on Palantir, it is a different route to enterprise intelligence, built bottom up from knowledge
governance to trustworthy decisions and simulation. The comparison is drawn against knowledge
graphs and vector stores, which is the category we actually differ from.
Philosophy is now two paragraphs instead of one, and the two languages are deliberately not
literal translations of each other. Em dashes are gone from the English file entirely.
The demo
The placeholder is replaced by the attachment from #152.
It is anchored to a published discussion rather than an orphaned upload, so nothing depends on
an asset that no content references.
<video>tags do not survive GitHub's sanitiser in a repository context, and neither does arelative
src, so the bare attachment URL is the only form that renders a player. The commentabove it now says so.
Two things in the table were no longer true
Cold start. It claimed every knowledge base ships with a built-in ontology of person,
organization, project, product, event, concept, location "and the relations among them". None of
that is still seeded: built-in classes went in 0009, and the seed relations went across 0010,
#125 and 0011.
graph.rssays it plainly, that a base has only the vocabulary its user imported.Cold start comes from the packs now, which was the point of 0008, so the row names them and links
to a pack request.
Encoding detection was described as being for Chinese sources.
chardetngis Mozilla'sgeneral detector and covers the whole legacy set, so the row no longer scopes it to one language.
What was added
Capabilities present in the product but absent from the table: a complete application, the agent
harness and its multi-turn tool calling, conflict detection as its own entry, and decision
intelligence marked in development and linked to the roadmap. Mapping exploration was added to
ontology-driven querying, and role levels to permissions.
The nine existing entries keep their content. English rows went from 792 words to about 600 by
cutting mechanism detail that belongs in the ADRs, not by dropping claims. The BIRD Mini-Dev
figures are now a link rather than four numbers inline.
The roadmap is aligned across both languages.