mirror of
https://github.com/getzep/graphiti.git
synced 2024-09-08 19:13:11 +03:00
895afc7be1
* chore: Add romeo runner * fix: Linter * wip * wip dump * chore: Update romeo parser * chore: Anthropic model fix * wip * allbirds * allbirds runner * format * wip * wip * mypy updates * update * remove r * update tests * format * wip * chore: Strategically update the message * rebase and fix import issues * Update package imports for graphiti_core in examples and utils * nits * chore: Update OpenAI GPT-4o model to gpt-4o-2024-08-06 * implement groq * improvments & linting * cleanup and nits * Refactor package imports for graphiti_core in examples and utils * Refactor package imports for graphiti_core in examples and utils * implement diskcache * remove debug stuff * log cache hit when debugging only * Improve LLM config. Fix bugs (#41) Refactor LLMConfig class to allow None values for model and base_url * chore: Resolve mc --------- Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com> Co-authored-by: prestonrasmussen <prasmuss15@gmail.com>
78 lines
2.4 KiB
Python
78 lines
2.4 KiB
Python
"""
|
|
Copyright 2024, Zep Software, Inc.
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License");
|
|
you may not use this file except in compliance with the License.
|
|
You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
See the License for the specific language governing permissions and
|
|
limitations under the License.
|
|
"""
|
|
|
|
import os
|
|
import re
|
|
|
|
|
|
def parse_script(filename):
|
|
current_speaker = None
|
|
current_speech = []
|
|
messages = []
|
|
|
|
with open(filename) as file:
|
|
for line in file:
|
|
line = line.strip()
|
|
|
|
# Check if this line is a new speaker
|
|
if (
|
|
line
|
|
and line.isupper()
|
|
and not line.startswith('ACT')
|
|
and not line.startswith('SCENE')
|
|
):
|
|
# If we have a current speaker, save their message
|
|
if current_speaker:
|
|
messages.append((current_speaker, ' '.join(current_speech)))
|
|
|
|
# Start a new speech
|
|
current_speaker = line
|
|
current_speech = []
|
|
elif line and not line.startswith('[') and current_speaker:
|
|
# Add this line to the current speech
|
|
current_speech.append(line)
|
|
|
|
# Add the last speech
|
|
if current_speaker:
|
|
messages.append((current_speaker, ' '.join(current_speech)))
|
|
|
|
return messages
|
|
|
|
|
|
def escape_special_characters(text):
|
|
# Define the special characters to remove
|
|
special_chars = r'+-&|!(){}[]^"~*?:\/'
|
|
|
|
# Use regex to replace all special characters with an empty string
|
|
return re.sub(f'[{re.escape(special_chars)}]', '', text)
|
|
|
|
|
|
# Test the function with a sample line from your text
|
|
sample_text = "GREGORY: To move is to stir; and to be valiant is to stand\\: therefore, if thou art moved, thou runn'st away."
|
|
escaped_text = escape_special_characters(sample_text)
|
|
print(escaped_text)
|
|
|
|
|
|
def get_romeo_messages():
|
|
file_path = 'romeo_act2.txt'
|
|
script_dir = os.path.dirname(__file__)
|
|
relative_path = os.path.join(script_dir, file_path)
|
|
# Use the function with escaping
|
|
return [
|
|
(speaker, escape_special_characters(speech))
|
|
for speaker, speech in parse_script(relative_path)
|
|
]
|