The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
ollama
is now supported as a provider, both for
generative and embedding models. This, of course, requires a local
ollama server to be up.get_batched_embeddings
was giving ugly column names.
Now they go from v1
to vn
setup_llm_parallel()
changed parameter order to accept
numeric positional argument for workers
.llm_mutate()
adds a shorthand form:
llm_mutate(answer = "<prompt>" | c(system=..., user=...), .config=...)
.llm_mutate()
gains .structured
flag: set
.structured = TRUE
to enable JSON output with automatic
parsing (equivalent to calling
llm_mutate_structured()
).llm_mutate_structured()
now supports shorthand syntax:
llm_mutate_structured(result = "{text}", .schema = schema)
..fields
documentation to clarify
auto-extraction behavior and nested path support..schema = NULL
enables JSON mode without
strict schema validation..category_from_condition
in parallel utilities.build_factorial_experiments()
documentation to
correctly describe return value columns.call_llm_par()
default value for
backoff_factor
parameter (now correctly documented as
3).@importFrom purrr
declarations for
imported functions.claude
calls.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.