forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
42 lines
1.2 KiB
Python
42 lines
1.2 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
import re
|
|
from typing import List
|
|
|
|
from langchain.schema import OutputParserException
|
|
|
|
|
|
def parse_json_markdown(json_string: str) -> dict:
|
|
# Try to find JSON string within triple backticks
|
|
match = re.search(r"```(json)?(.*?)```", json_string, re.DOTALL)
|
|
|
|
# If no match found, assume the entire string is a JSON string
|
|
if match is None:
|
|
json_str = json_string
|
|
else:
|
|
# If match found, use the content within the backticks
|
|
json_str = match.group(2)
|
|
|
|
# Strip whitespace and newlines from the start and end
|
|
json_str = json_str.strip()
|
|
|
|
# Parse the JSON string into a Python dictionary
|
|
parsed = json.loads(json_str)
|
|
|
|
return parsed
|
|
|
|
|
|
def parse_and_check_json_markdown(text: str, expected_keys: List[str]) -> dict:
|
|
try:
|
|
json_obj = parse_json_markdown(text)
|
|
except json.JSONDecodeError as e:
|
|
raise OutputParserException(f"Got invalid JSON object. Error: {e}")
|
|
for key in expected_keys:
|
|
if key not in json_obj:
|
|
raise OutputParserException(
|
|
f"Got invalid return object. Expected key `{key}` "
|
|
f"to be present, but got {json_obj}"
|
|
)
|
|
return json_obj
|