LocalAI/core
Ettore Di Giacinto 491e1d752b
feat(functions): relax mixedgrammars (#2365)
* feat(functions): relax mixedgrammars

Extend even more the functionalities and when mixed mode is enabled,
tolerate also both strings and JSON in the result - in this case we make
sure that the JSON can be correctly parsed.

This also updates the examples and the gallery model to configure the
grammar.

The changeset also breaks current function/grammar configuration as it
reserves now a stanza in the YAML config.

For example:

```yaml
function:
  grammar:
    # This allows the grammar to also return messages
    mixed_mode: true
    # Suffix to add to the grammar
    # prefix: '<tool_call>\n'
    # Force parallel calls in the grammar
    # parallel_calls: true
```

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor, add a way to disable mixed json and freestring

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix linting issues

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-22 00:14:16 +02:00
..
backend feat(llama.cpp): add flash_attention and no_kv_offloading (#2310) 2024-05-13 19:07:51 +02:00
cli feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) 2024-05-20 19:17:59 +02:00
clients feat(store): add Golang client (#1977) 2024-04-16 15:54:14 +02:00
config dependencies(grpcio): bump to fix CI issues (#2362) 2024-05-21 14:33:47 +02:00
dependencies_manager feat(webui): statically embed js/css assets (#2348) 2024-05-19 18:24:27 +02:00
http feat(functions): relax mixedgrammars (#2365) 2024-05-22 00:14:16 +02:00
p2p feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) 2024-05-20 19:17:59 +02:00
schema feat(grammar): support models with specific construct (#2291) 2024-05-12 01:13:22 +02:00
services feat(webui): ux improvements (#2247) 2024-05-07 01:17:07 +02:00
startup feat(startup): show CPU/GPU information with --debug (#2241) 2024-05-05 09:10:23 +02:00
application.go refactor(application): introduce application global state (#2072) 2024-04-29 17:42:37 +00:00