mirror of
https://git.pumpin.online/funkpower/catena.git
synced 2026-10-22 18:57:14 +00:00
funkpower
0b849c39c4
The hashed bag of words asks only whether two stretches repeat the same words, and cannot tell that ships and vessels are one subject. An embedding can. segment_with takes one vector per window and falls back to the words when it is given none, or the wrong number of them — a caller that embedded some other recording's windows is asking about that recording. windows_of gives the text to embed, in the order the vectors come back in, so nobody has to reimplement the windowing pass to use this. Bound in all three languages, and on the command line as --windows and --embeddings, which pipe through emb. The C ABI version goes to 2: catena_segment_cues gained an argument.
96 lines
3.6 KiB
C
96 lines
3.6 KiB
C
/*
|
|
* catena — the libraries behind one surface, for C callers.
|
|
*
|
|
* Text goes in as NUL-terminated UTF-8; records come back as a
|
|
* NUL-terminated JSON array, the same document the command line writes and
|
|
* under the same stability promise. Release every returned string with
|
|
* catena_string_free.
|
|
*
|
|
* A function that can fail returns NULL and leaves a message in
|
|
* catena_last_error, which is thread-local.
|
|
*
|
|
* Every function is safe to call from any thread.
|
|
*
|
|
* Licence: MPL-2.0. See https://git.pumpin.online/funkpower/catena
|
|
*/
|
|
#ifndef CATENA_H
|
|
#define CATENA_H
|
|
|
|
#include <stddef.h>
|
|
#include <stdint.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/* Bumped when the meaning or signature of anything here changes. Additions
|
|
* leave it alone. Check it against CATENA_ABI_VERSION at load time. */
|
|
#define CATENA_ABI_VERSION 2u
|
|
|
|
unsigned int catena_abi_version(void);
|
|
|
|
/* Why the last call on this thread failed, or NULL if none did. Valid until
|
|
* the next failing call on the same thread. Do not free. */
|
|
const char *catena_last_error(void);
|
|
|
|
/* Release a string this library returned. NULL is allowed. */
|
|
void catena_string_free(char *text);
|
|
|
|
/* Cut markdown into retrievable passages. Returns a JSON array of chunks.
|
|
* Zero for a budget means that budget's default. */
|
|
char *catena_chunk_markdown(const char *markdown,
|
|
size_t target,
|
|
size_t overlap,
|
|
size_t min_tokens,
|
|
size_t hard_max);
|
|
|
|
/* Clean converted markdown. Non-zero `pages` normalises page markers as
|
|
* well, which is not idempotent. Returns the cleaned text. */
|
|
char *catena_scrub(const char *markdown, int pages);
|
|
|
|
/* How many tokens a string is. Zero on error. */
|
|
size_t catena_count_tokens(const char *text);
|
|
|
|
/* Read any of the subtitle formats. Returns a JSON array of cues. */
|
|
char *catena_parse_subtitles(const char *content, int keep_repeats);
|
|
|
|
/* Pack cues into passages. `cues` is a JSON array of cues. Zero for either
|
|
* budget means the default. Returns a JSON array of chunks. */
|
|
char *catena_pack_cues(const char *cues, double seconds, size_t max_tokens);
|
|
|
|
/* Cut a timed transcript into topic chapters. `cues` is a JSON array of
|
|
* cues. `embeddings` is a JSON array of one vector per window, or NULL to
|
|
* compare windows by the words they repeat. A duration of zero or less is
|
|
* taken from the last cue. Returns a JSON array of segments. */
|
|
char *catena_segment_cues(const char *cues,
|
|
double duration,
|
|
const char *embeddings);
|
|
|
|
/* The text of each window a transcript is measured in, in the order
|
|
* catena_segment_cues expects vectors back. Returns a JSON array of
|
|
* strings. */
|
|
char *catena_cue_windows(const char *cues);
|
|
|
|
/* Split a collection into the works inside it. Returns a JSON array of
|
|
* sections, or NULL when the document is one work rather than a collection —
|
|
* an answer, not a failure; the reason is in catena_last_error. */
|
|
char *catena_split_collection(const char *markdown);
|
|
|
|
/* Fuse ranked lists into one. `hits` is a JSON array; `weights` a JSON object
|
|
* of channel to weight, or NULL. Zero `k` means the default, zero `limit`
|
|
* means all of them. Returns a JSON array. */
|
|
char *catena_fuse_hits(const char *hits,
|
|
double k,
|
|
const char *weights,
|
|
size_t limit);
|
|
|
|
/* Say what a file is from its first bytes and its name. Returns a JSON doc
|
|
* record. */
|
|
char *catena_identify(const char *name, const uint8_t *data, size_t len);
|
|
|
|
#ifdef __cplusplus
|
|
} /* extern "C" */
|
|
#endif
|
|
|
|
#endif /* CATENA_H */
|