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
This commit is contained in:
parent
1943c01981
commit
5b7b0ac8df
28 changed files with 7607 additions and 3571 deletions
74
examples/json-schema-pydantic-example.py
Normal file
74
examples/json-schema-pydantic-example.py
Normal file
|
@ -0,0 +1,74 @@
|
|||
# Usage:
|
||||
#! ./server -m some-model.gguf &
|
||||
#! pip install pydantic
|
||||
#! python json-schema-pydantic-example.py
|
||||
|
||||
from pydantic import BaseModel, TypeAdapter
|
||||
from annotated_types import MinLen
|
||||
from typing import Annotated, List, Optional
|
||||
import json, requests
|
||||
|
||||
if True:
|
||||
|
||||
def create_completion(*, response_model=None, endpoint="http://localhost:8080/v1/chat/completions", messages, **kwargs):
|
||||
'''
|
||||
Creates a chat completion using an OpenAI-compatible endpoint w/ JSON schema support
|
||||
(llama.cpp server, llama-cpp-python, Anyscale / Together...)
|
||||
|
||||
The response_model param takes a type (+ supports Pydantic) and behaves just as w/ Instructor (see below)
|
||||
'''
|
||||
if response_model:
|
||||
type_adapter = TypeAdapter(response_model)
|
||||
schema = type_adapter.json_schema()
|
||||
messages = [{
|
||||
"role": "system",
|
||||
"content": f"You respond in JSON format with the following schema: {json.dumps(schema, indent=2)}"
|
||||
}] + messages
|
||||
response_format={"type": "json_object", "schema": schema}
|
||||
|
||||
data = requests.post(endpoint, headers={"Content-Type": "application/json"},
|
||||
json=dict(messages=messages, response_format=response_format, **kwargs)).json()
|
||||
if 'error' in data:
|
||||
raise Exception(data['error']['message'])
|
||||
|
||||
content = data["choices"][0]["message"]["content"]
|
||||
return type_adapter.validate_json(content) if type_adapter else content
|
||||
|
||||
else:
|
||||
|
||||
# This alternative branch uses Instructor + OpenAI client lib.
|
||||
# Instructor support streamed iterable responses, retry & more.
|
||||
# (see https://python.useinstructor.com/)
|
||||
#! pip install instructor openai
|
||||
import instructor, openai
|
||||
client = instructor.patch(
|
||||
openai.OpenAI(api_key="123", base_url="http://localhost:8080"),
|
||||
mode=instructor.Mode.JSON_SCHEMA)
|
||||
create_completion = client.chat.completions.create
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
class QAPair(BaseModel):
|
||||
question: str
|
||||
concise_answer: str
|
||||
justification: str
|
||||
|
||||
class PyramidalSummary(BaseModel):
|
||||
title: str
|
||||
summary: str
|
||||
question_answers: Annotated[List[QAPair], MinLen(2)]
|
||||
sub_sections: Optional[Annotated[List['PyramidalSummary'], MinLen(2)]]
|
||||
|
||||
print("# Summary\n", create_completion(
|
||||
model="...",
|
||||
response_model=PyramidalSummary,
|
||||
messages=[{
|
||||
"role": "user",
|
||||
"content": f"""
|
||||
You are a highly efficient corporate document summarizer.
|
||||
Create a pyramidal summary of an imaginary internal document about our company processes
|
||||
(starting high-level, going down to each sub sections).
|
||||
Keep questions short, and answers even shorter (trivia / quizz style).
|
||||
"""
|
||||
}]))
|
Loading…
Add table
Add a link
Reference in a new issue