From 5b7b0ac8dfdd800c0fd0dc69b69991e8cb19fb46 Mon Sep 17 00:00:00 2001
From: Olivier Chafik <ochafik@users.noreply.github.com>
Date: Thu, 21 Mar 2024 11:50:43 +0000
Subject: json-schema-to-grammar improvements (+ added to server) (#5978)

* json: fix arrays (disallow `[,1]`)

* json: support tuple types (`[number, string]`)

* json: support additionalProperties (`{[k: string]: [string,number][]}`)

* json: support required / optional properties

* json: add support for pattern

* json: resolve $ref (and support https schema urls)

* json: fix $ref resolution

* join: support union types (mostly for nullable types I think)

* json: support allOf + nested anyOf

* json: support any (`{}` or `{type: object}`)

* json: fix merge

* json: temp fix for escapes

* json: spaces in output and unrestricted output spaces

* json: add typings

* json:fix typo

* Create ts-type-to-grammar.sh

* json: fix _format_literal (json.dumps already escapes quotes)

* json: merge lit sequences and handle negatives

{"type": "string", "pattern": "^({\"question\": \"[^\"]+\", \"response\": \"[^\"]+\"}\\n)+$"}

* json: handle pattern repetitions

* Update json-schema-to-grammar.mjs

* Create regex-to-grammar.py

* json: extract repeated regexp patterns to subrule

* Update json-schema-to-grammar.py

* Update json-schema-to-grammar.py

* Update json-schema-to-grammar.py

* json: handle schema from pydantic Optional fields

* Update json-schema-to-grammar.py

* Update json-schema-to-grammar.py

* Update ts-type-to-grammar.sh

* Update ts-type-to-grammar.sh

* json: simplify nullable fields handling

* json: accept duplicate identical rules

* json: revert space to 1 at most

* json: reuse regexp pattern subrules

* json: handle uuid string format

* json: fix literal escapes

* json: add --allow-fetch

* json: simplify range escapes

* json: support negative ranges in patterns

* Delete commit.txt

* json: custom regex parser, adds dot support & JS-portable

* json: rm trailing spaces

* Update json-schema-to-grammar.mjs

* json: updated server & chat `( cd examples/server && ./deps.sh )`

* json: port fixes from mjs to python

* Update ts-type-to-grammar.sh

* json: support prefixItems alongside array items

* json: add date format + fix uuid

* json: add date, time, date-time formats

* json: preserve order of props from TS defs

* json: port schema converter to C++, wire in ./server

* json: nits

* Update json-schema-to-grammar.cpp

* Update json-schema-to-grammar.cpp

* Update json-schema-to-grammar.cpp

* json: fix mjs implementation + align outputs

* Update json-schema-to-grammar.mjs.hpp

* json: test C++, JS & Python versions

* json: nits + regen deps

* json: cleanup test

* json: revert from c++17 to 11

* json: nit fixes

* json: dirty include for test

* json: fix zig build

* json: pass static command to std::system in tests (fixed temp files)

* json: fix top-level $refs

* json: don't use c++20 designated initializers

* nit

* json: basic support for reserved names `{number:{number:{root:number}}}`

* Revamp test cmake to allow args (WORKING_DIRECTORY needed for JSON test)

* json: re-ran server deps.sh

* json: simplify test

* json: support mix of additional props & required/optional

* json: add tests for some expected failures

* json: fix type=const in c++, add failure expectations for non-str const&enum

* json: test (& simplify output of) empty schema

* json: check parsing in test + fix value & string refs

* json: add server tests for OAI JSON response_format

* json: test/fix top-level anyOf

* json: improve grammar parsing failures

* json: test/fix additional props corner cases

* json: fix string patterns (was missing quotes)

* json: ws nit

* json: fix json handling in server when there's no response_format

* json: catch schema conversion errors in server

* json: don't complain about unknown format type in server if unset

* json: cleaner build of test

* json: create examples/json-schema-pydantic-example.py

* json: fix date pattern

* json: move json.hpp & json-schema-to-grammar.{cpp,h} to common

* json: indent 4 spaces

* json: fix naming of top-level c++ function (+ drop unused one)

* json: avoid using namespace std

* json: fix zig build

* Update server.feature

* json: iostream -> fprintf

* json: space before & refs for consistency

* json: nits
---
 examples/server/utils.hpp | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'examples/server/utils.hpp')

diff --git a/examples/server/utils.hpp b/examples/server/utils.hpp
index cc5fce69..ff146893 100644
--- a/examples/server/utils.hpp
+++ b/examples/server/utils.hpp
@@ -373,10 +373,21 @@ static json oaicompat_completion_params_parse(
     llama_params["tfs_z"]             = json_value(body,   "tfs_z",             default_sparams.tfs_z);
     llama_params["n_keep"]            = json_value(body,   "n_keep",            0);
 
-    if (body.count("grammar") != 0) {
+    if (body.contains("grammar")) {
         llama_params["grammar"] = json_value(body, "grammar", json::object());
     }
 
+    if (body.contains("response_format")) {
+        auto response_format = json_value(body, "response_format", json::object());
+        if (response_format.contains("type")) {
+            if (response_format["type"] == "json_object") {
+                llama_params["json_schema"] = json_value(response_format, "schema", json::object());
+            } else {
+                throw std::runtime_error("response_format type not supported: " + response_format["type"].dump());
+            }
+        }
+    }
+
     // Handle 'stop' field
     if (body.contains("stop") && body["stop"].is_string()) {
         llama_params["stop"] = json::array({body["stop"].get<std::string>()});
-- 
cgit v1.2.3