SingleDatabaseSession owns the store, the repositories and the vacuum
machinery, so nothing above has to ask whether it has a store. The client
keeps every name callers already use.
DatabaseScope.resolve reads configuration and at most one selector; a
DatabaseRef carries the configured name and a location already resolved to
a URI or a path, so a path a caller names is never reinterpreted. Nothing
consumes it yet.
An embedder is a function of configuration, not of a database, and the
databases in a selection share one, so a client covering a set builds it
on first use and closes it on teardown. Operations that need one database
say so instead of surfacing a missing store.
An image query has no text to match, so it is vector-only whatever the
caller asked for, and full-text search embeds nothing, so it needs no
agreement on embedders.
`first_found` replaces the client's private version and the capability's
sequential one. The info modal reports through the connection the client
already holds.
A title repeats within a corpus and across databases, so a substring
match on the displayed name widened the filter to documents the user did
not pick. The label names the database.
Each database owns an embedder, so embedding per database cost a round
trip each. One database still embeds inside the repository, which returns
early for a filter that matches nothing.
A blank name is falsy, so source routing reads it as absent, and a blank
location resolves to the working directory. `is_read_only` reports the
mode the client was opened with, which a client covering a set can answer
without a store.
Document.source names the configured database, as SearchResult and
Citation already do. A listing spanning databases is unreadable
without it, and `--database NAME list` could not name the one it
opened.
`get_document_by_id`, `get_document_by_uri` and `get_chunk_by_id` read
through repositories a client covering a set does not have, so a lookup by
identifier raised AttributeError and `resolve_document` with it. An
identifier says nothing about which database holds it, so every database is
asked at once and the first that has it, in configured order, answers.
On the evaluation side, `--db` overrides the configured set as the CLI
documents, and population refuses a set rather than ingesting into a
database the run would not read. A case filter matching nothing raises
instead of reporting 0.0000 as though it were a score.
Reciprocal rank fusion compares ranks, so every database contributes its
own best matches whether or not they answer the question, and results from
databases holding nothing relevant displace better ones. Measured on one
corpus split three ways over 3,045 queries: retrieval MAP 0.6044 without a
reranker against 0.9798 for the same corpus in a single database, and
0.9918 against 0.9914 with one.
A run over several databases could report which documents were cited but
not which database grounded the answer: `_result_from_run` walked the
citation index for `document_uri` and dropped `Citation.source`. The
distribution is not recoverable from the report afterwards, so a sharded
run would have measured everything except attribution.
`cited_sources` is one entry per cited chunk, in citation order, empty
where the database is unnamed.
The runner passed the dataset's path to every arm, which opens one database
and is what makes `--db` meaningful. A run over `lancedb.databases` has to
pass none instead, so the client resolves the set, and `DatasetSpec.covers_a_set`
is the one place that decides which of the two a run is.
A capability covering several databases received `source` on every document
and search result and never used it: asked how many documents were in each
database, the model read the titles and answered that there was one corpus
of 67,581. The instruction files enumerate what a result carries, and both
enumerations had gone stale.
The note follows what the capability opens rather than what the
configuration names, through `covers_several_databases`: an explicit
`db_path` or a lent client covering one database is instructed as before,
as is every `uri` or path deployment and every eval dataset. The analysis
note separates the three interfaces, since they differ: an
`analysis_search` result carries a `Database:` line, in-code `search` and
`list_documents` return `source`, and the mounted files carry neither.
The modal listed every document and mounted a checkbox per document, so a
corpus of tens of thousands never finished rendering: 67k sequential
mounts across two databases, and the same for one database that size.
Titles repeat at that scale too, and the ids were derived from the title,
so they collided.
It shows a page of 200 now, mounted in one call and identified by
position, and the search box asks the database for the rest on enter,
matching titles and URIs. Typing still narrows the page on screen, for
feedback while typing. `search_filter` escapes the term, which is
whatever was typed.
A federated listing takes its window across the databases rather than
filling it from the first one: concatenating hid every database after
whichever was listed first, which for a set of a thousand papers and
sixty thousand articles meant a page of papers alone. Sorting would not
have helped, since document ids and article titles sort into separate
runs, so the page is picked by interleaving and the modal sorts it for
display.
Chat answers with the same capabilities `ask` does, so it federates as
naturally as `ask` and `analyze` — but it went through the one-database
guard and refused a configured set outright, which left no way to chat
across several databases.
The guard was the visible half. `run_chat` also defaulted `db_path` to the
single default path whenever it was None, so lifting the refusal alone
would still have opened one database. It now leaves the path unresolved
when `lancedb.databases` names the set, and the client resolves it.
Listing and counting documents fan out over the set, which is what the
document filter reads, and visual grounding resolves the database holding
the cited chunk through the citation's source: chunks, pages and bounding
boxes all come from that one database. A limit on a listing means that
many documents in total, not that many per database.
The info modal reports every database it covers, each under its
configured name and without its location, since names are the only
identity that leaves the configuration. `database_lines` is what one
database reports about itself, shared by both paths, and it reports a
failure as a line so one unreachable database does not cost the report on
the others.
`inspect` stays a one-database command. It browses one database's
documents and chunks, so a set has nothing to show it.
The CLI reports this error, and importing it from the settings repository
pulled lancedb onto the CLI's import path. Deferring the import into cli()
bought nothing, since cli() runs on every invocation: it cost about 1.9
seconds on a cold start, `--help` included.
It now sits beside the other store exceptions, in a module that imports
nothing, and every importer points there.
A database whose stored embedder disagrees with the configuration raised
ConfigMismatchError through Typer, so the operator got a traceback wrapped
around the one message that says what to run, while every sibling failure
exits with its message. It joins the errors the CLI reports.
Imported inside cli() rather than at module scope: the settings module
pulls in lancedb, and importing the CLI must not pay for it.
lancedb.databases, the sources argument and the --database selector had no
documentation. Adds a Several Databases section to the storage
configuration page covering the name-to-location map, its mutual
exclusion with uri, the shared embedding configuration the set requires,
and which commands cover the set against which work on one. Adds a
Searching Several Databases section to the Python API page, --database to
the CLI's global options, the key to the sample configuration, and one
README feature line.
Chunk 2 gave search a configured set to fan out over. ask and analyze
covered one database still: the RAG capability had no way to be told which
databases a question spanned, and the analysis sandbox mounted one
document tree.
The selection travels as sources on EvidenceState, beside the filter it
scopes with, so both capabilities read it the same way. clients_covering
is the one rule that turns a selection into clients, used by search, the
sandbox mount and the cite fallback, so a question scoped to some
databases cannot search, mount or cite another. Citations carry the
database they came from, and format_for_agent names it, so the model can
attribute evidence while it answers rather than only afterwards.
The sandbox keeps one flat /documents/{id}/ namespace and resolves each id
to the client holding it, which rests on ids being UUID4. A database
copied from another breaks that, so an id held twice is refused rather
than resolved to whichever arrived last.
On the CLI, search, ask and analyze cover the configured set and label
each result with its database. Every other command works on one, named
with --database NAME (a name reaches a database behind a URI, which --db
cannot) or --db PATH, and refuses a set it cannot choose from instead of
silently reading the default database. Cold databases open together, so a
first query costs the slowest open rather than their sum.
`ask(sources=[…])` scopes a question to some of the configured databases, carried
on the capability state so its search tool searches those. `Citation.source` names
the database a cited chunk came from, resolved from the search results the model
saw, which already carry it.
Context expansion routes each result through the database it came from: a
federating client has no repositories of its own.
The cite fallback, which looks up an id absent from this run's results, searches
only the selected databases. A chunk id says nothing about which database holds
it, so placing one means asking, and asking outside the selection would let a
question scoped to some databases cite another.
The loosely-specced client mocks in the capability tests now say they stand in for
a single-database client. A bare AsyncMock answers any attribute with a truthy
Mock, so `_federated` sent the fallback down the multi-database branch, and
`_source` reached a validated field.
`lancedb.databases` maps a name to a location, mutually exclusive with `uri`.
`search(sources=[…])` selects which to search, `sources=None` searches all of them
and `sources=[]` searches none; `SearchResult.source` carries the configured name,
so a path or URI never leaves the configuration. A database named in config keeps
its name even when it is the only one configured; only a legacy single `uri`
leaves `source` unset.
Databases open on first use, not at entry. Which are searched is a per-query
choice, so a set of 25 queried a few at a time opens a few, and a database nobody
asked for can neither fail a query nor be opened for nothing.
A named database that fails to open raises `SourceUnavailableError` naming it,
raised outside the handler so the original is not attached at all. A local failure
spells out the absolute path and an object-store failure can carry the bucket;
`from None` would only stop that being printed, leaving it on `__context__` for
anything that walks the chain. A legacy `uri` client has no name to report
instead, so its error passes through unchanged.
Candidates are fetched concurrently, then fused before anything is ranked. A
configured reranker scores the union, which is what makes ranking across
databases tractable: it compares query against document and does not care where a
candidate came from. Without one, reciprocal rank fusion over the per-database
rankings, since scores from separate indexes are not comparable. Enrichment then
runs on the survivors through the database each came from, concurrently, so it
costs what a single-database search costs.
The over-fetch decision and the reranker belong to the federating client alone.
Deciding per database would have each consult its own, and a local reranker loads
model weights per instance. It is built only for a text query, and closed once by
the client that owns it.
A location without a scheme is opened as a local path rather than through
`lancedb.uri`. Routing it through `uri` had `ConnectionMode` classify it as object
storage, which opens a missing database instead of reporting it.
With several databases configured, `store` and the repositories are left unset:
they have no unambiguous meaning across a set, and picking one silently would be
worse than the error.
`search` fetched, reranked and truncated in one pass, with the reranker's
over-fetch and the reranking itself interleaved in the same branch. Searching
several databases needs to fuse their candidates before anything is ranked, so
the phases have to be separable.
`_fetch` returns one database's candidates, over-fetching only when a reranker
will re-order them. `_rank` orders and cuts them, leaving an image query's vector
ranking alone since there is no text for a reranker to score against. The
over-fetch multiplier is named rather than a literal 10 at the point of use.
Both check the query type before reading `client.reranker`, which is a
cached_property that builds the reranker on first access and loads model weights
for a local one. An image query never used it and must not start.
No behaviour change: the same suite passes, and the search outputs digest
identically to before.
Port 11433 serves nothing; Qwen3-Reranker-4B is on 11455. Qwen3.6 spends
its budget reasoning before it answers, and its 131072 window leaves ample
input space at 32768.
The skill assumed the Logfire MCP is loaded. It is not loaded in every
session, which left no way to inspect a run at all. Document the HTTP query
API as the fallback, including the mandatory min_timestamp, the API keys
replacing read tokens, and the project-scoping trap: a key for the wrong
project authenticates and returns zero rows rather than erroring.
Also record three things that produced wrong readings in practice:
assertions/scores/metrics are keys inside the attributes column rather than
columns, one exception is emitted once per span level so failures must be
counted at case level, and assertion_pass_rate drops unjudged cases from its
denominator so judged and floor rates have to be quoted together.
Add a section for monitoring a run that is still in flight, since an eval
prints nothing until it finishes: case-span progress, the serial-execution
check that makes an ETA valid, and the per-case diagnostic attributes.
Vendor the query helper next to the skill so it does not point at a path
outside the repo, and derive its region from the key prefix.
`Agent.from_spec` raised `TypeError` on `RAGCapability` and `AnalysisCapability`,
whose constructors take a state class, packaged instruction text and a tool-name
set, and silently omitted both from the generated spec schema. The two
zero-configuration capabilities constructed but with `id=None`, so pydantic-ai's
duplicate-id rejection no longer held and a spec could register two citation
policies, defeating the single-decision-maker invariant.
Override `from_spec` on all four, delegating to `create_capability()` so ids and
instructions come from one place. The spec surface is `db_path`, `config`,
`defer_loading`, `request_limit` and `vision`; a live `HaikuRAG` client stays out
of it, and a `config` mapping is validated through `AppConfig`.
The documented `HaikuRAG("knowledge.lancedb")` and `rag(db_path="my.lancedb")`
forms both raised `AttributeError: 'str' object has no attribute 'exists'`.
`Store.__init__` assigned its argument to a `Path`-annotated attribute without
coercing, and `resolve_db_path` returned a non-None argument unchanged. Every
runnable example wraps the path in `Path(...)`, which is why it survived.
Coerce in `Store.__init__` and `resolve_db_path`; widen the annotations on
`Store`, `HaikuRAG` and both `create_capability` factories to accept `str`.
urlparse().path keeps the leading slash in front of a Windows drive, so
file:///C:/docs/a.pdf read as \C:\docs\a.pdf and the ingester reported
"File does not exist" for every file it discovered. url2pathname is the
stdlib conversion that strips it, per platform.
Four sites each decided both "is this local" and "what path is this":
FSSource._uri_to_path and supports, resolve_adhoc_fetcher,
create_document_from_source and check_source_accessible, and convert.
is_local_uri and uri_to_path in haiku.rag.uri own those two decisions now,
which closes two more cases of the same root cause. A bare C:\docs\a.pdf
parses with scheme "c", so add-src raised "No source adapter for URI scheme
'c'" and convert silently treated the path as raw text. And convert and
check_source_accessible never percent-decoded at all, so a file named
a[b] c.md read as missing on Linux and macOS too.
A file URI's host is reattached after conversion rather than passed to
url2pathname, which as of 3.14 rejects a non-local authority off Windows.
file:////server/share is the empty-authority spelling of a UNC path, its
host being the first path segment, so that host is normalised into the
authority before conversion. Output is identical on 3.12, 3.13 and 3.14.
The ad-hoc FS fetcher roots at the path's own anchor rather than "/", which
on Windows is only the current drive.
test_uri.py runs on ubuntu, macos and windows across 3.13 and 3.14 without
the project installed: --noconftest because the repo conftest imports
dependencies that job does not need, and -o addopts= to drop the
repository's -n auto. The Windows legs are what cover the drive conversion.
Fixes#574.
Sixty-three comments said what the next statement already said: # Connect to
LanceDB above connect_lancedb, # Path object above isinstance(source, Path),
# Get page numbers from provenance above the prov loop, # Clear and populate
results above list_view.clear(). They cost a read and carry nothing.
The line is whether a comment restates one statement or labels a phase. Phase
labels stay: the migrations keep # Create staging table with new schema and
# Copy from staging to final table in batches, each heading ten lines of a
long procedure. So do comments carrying a fact the code cannot: the
merge_insert update-only note on document_meta, why the poller builds sources
eagerly, why create_document_from_source returns a list for directories, that
indexes need training data, the field-group markers in the config models, and
the file:// URL-encoding note in create_document_from_source.
capabilities/ is untouched. Its docstrings sit next to prompt surface, and
changing them needs an eval to back it.
The cassette-recording docs were wrong three ways. They named
tests/test_qa.py::test_qa_anthropic, which no longer exists; they targeted
whole modules, so a rewrite would re-record cassettes for services the
recorder is not running; and they used COHERE_API_KEY where the SDK reads
CO_API_KEY. docs/development.md now names exact tests with -n0, and the keyed
example is test_cohere_reranker, which owns the one cassette recording
api.cohere.com.
