From 5b7b0ac8dfdd800c0fd0dc69b69991e8cb19fb46 Mon Sep 17 00:00:00 2001 From: Olivier Chafik 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/tests/features/security.feature | 16 ++++++++++++++++ examples/server/tests/features/server.feature | 16 ++++++++++++++++ examples/server/tests/features/steps/steps.py | 17 +++++++++++++++++ 3 files changed, 49 insertions(+) (limited to 'examples/server/tests') diff --git a/examples/server/tests/features/security.feature b/examples/server/tests/features/security.feature index 1d6aa40e..eb82e7ac 100644 --- a/examples/server/tests/features/security.feature +++ b/examples/server/tests/features/security.feature @@ -37,6 +37,22 @@ Feature: Security | llama.cpp | no | | hackme | raised | + Scenario Outline: OAI Compatibility (invalid response formats) + Given a system prompt test + And a user prompt test + And a response format + And a model test + And 2 max tokens to predict + And streaming is disabled + Given an OAI compatible chat completions request with raised api error + + Examples: Prompts + | response_format | + | {"type": "sound"} | + | {"type": "json_object", "schema": 123} | + | {"type": "json_object", "schema": {"type": 123}} | + | {"type": "json_object", "schema": {"type": "hiccup"}} | + Scenario Outline: CORS Options Given a user api key llama.cpp diff --git a/examples/server/tests/features/server.feature b/examples/server/tests/features/server.feature index 45a988db..a2e0e5b3 100644 --- a/examples/server/tests/features/server.feature +++ b/examples/server/tests/features/server.feature @@ -70,6 +70,22 @@ Feature: llama.cpp server | codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 128 | (thanks\|happy\|bird\|Annabyear)+ | -1 | 64 | enabled | | + Scenario Outline: OAI Compatibility w/ response format + Given a model test + And a system prompt test + And a user prompt test + And a response format + And 10 max tokens to predict + Given an OAI compatible chat completions request with no api error + Then tokens are predicted matching + + Examples: Prompts + | response_format | n_predicted | re_content | + | {"type": "json_object", "schema": {"const": "42"}} | 5 | "42" | + | {"type": "json_object", "schema": {"items": [{"type": "integer"}]}} | 10 | \[ -300 \] | + | {"type": "json_object"} | 10 | \{ " Jacky. | + + Scenario: Tokenize / Detokenize When tokenizing: """ diff --git a/examples/server/tests/features/steps/steps.py b/examples/server/tests/features/steps/steps.py index 42cdd898..03f55f65 100644 --- a/examples/server/tests/features/steps/steps.py +++ b/examples/server/tests/features/steps/steps.py @@ -59,6 +59,7 @@ def step_server_config(context, server_fqdn, server_port): context.seed = None context.server_seed = None context.user_api_key = None + context.response_format = None context.tasks_result = [] context.concurrent_tasks = [] @@ -269,6 +270,11 @@ def step_max_tokens(context, max_tokens): context.n_predict = max_tokens +@step('a response format {response_format}') +def step_response_format(context, response_format): + context.response_format = json.loads(response_format) + + @step('streaming is {enable_streaming}') def step_streaming(context, enable_streaming): context.enable_streaming = enable_streaming == 'enabled' @@ -384,6 +390,9 @@ async def step_oai_chat_completions(context, api_error): enable_streaming=context.enable_streaming if hasattr(context, 'enable_streaming') else None, + response_format=context.response_format + if hasattr(context, 'response_format') else None, + seed=await completions_seed(context), user_api_key=context.user_api_key @@ -443,6 +452,8 @@ async def step_oai_chat_completions(context): if hasattr(context, 'n_predict') else None, enable_streaming=context.enable_streaming if hasattr(context, 'enable_streaming') else None, + response_format=context.response_format + if hasattr(context, 'response_format') else None, seed=await completions_seed(context), user_api_key=context.user_api_key if hasattr(context, 'user_api_key') else None) @@ -463,6 +474,8 @@ async def step_oai_chat_completions(context): if hasattr(context, 'n_predict') else None, enable_streaming=context.enable_streaming if hasattr(context, 'enable_streaming') else None, + response_format=context.response_format + if hasattr(context, 'response_format') else None, seed=context.seed if hasattr(context, 'seed') else context.server_seed @@ -745,6 +758,7 @@ async def oai_chat_completions(user_prompt, model=None, n_predict=None, enable_streaming=None, + response_format=None, seed=None, user_api_key=None, expect_api_error=None): @@ -770,6 +784,8 @@ async def oai_chat_completions(user_prompt, "stream": enable_streaming, "seed": seed } + if response_format is not None: + payload['response_format'] = response_format completion_response = { 'content': '', 'timings': { @@ -830,6 +846,7 @@ async def oai_chat_completions(user_prompt, model=model, max_tokens=n_predict, stream=enable_streaming, + response_format=payload.get('response_format'), seed=seed ) except openai.error.AuthenticationError as e: -- cgit v1.2.3