mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-27 11:41:51 +00:00
a0c2281540
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path
import toml
import subprocess
import re
ROOT_DIR = Path(__file__).parents[1]
def main():
for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
print(path)
with open(path, "rb") as f:
pyproject = tomllib.load(f)
try:
pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
"^1.10"
)
pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
"^0.5"
)
except KeyError:
continue
with open(path, "w") as f:
toml.dump(pyproject, f)
cwd = "/".join(path.split("/")[:-1])
completed = subprocess.run(
"poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
logs = completed.stdout.split("\n")
to_ignore = {}
for l in logs:
if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
path, line_no, error_type = re.match(
"^(.*)\:(\d+)\: error:.*\[(.*)\]", l
).groups()
if (path, line_no) in to_ignore:
to_ignore[(path, line_no)].append(error_type)
else:
to_ignore[(path, line_no)] = [error_type]
print(len(to_ignore))
for (error_path, line_no), error_types in to_ignore.items():
all_errors = ", ".join(error_types)
full_path = f"{cwd}/{error_path}"
try:
with open(full_path, "r") as f:
file_lines = f.readlines()
except FileNotFoundError:
continue
file_lines[int(line_no) - 1] = (
file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n"
)
with open(full_path, "w") as f:
f.write("".join(file_lines))
subprocess.run(
"poetry run ruff format .; poetry run ruff --select I --fix .",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
if __name__ == "__main__":
main()
```
97 lines
3.2 KiB
Python
97 lines
3.2 KiB
Python
"""Utilities for chat loaders."""
|
|
|
|
from copy import deepcopy
|
|
from typing import Iterable, Iterator, List
|
|
|
|
from langchain_core.chat_sessions import ChatSession
|
|
from langchain_core.messages import AIMessage, BaseMessage
|
|
|
|
|
|
def merge_chat_runs_in_session(
|
|
chat_session: ChatSession, delimiter: str = "\n\n"
|
|
) -> ChatSession:
|
|
"""Merge chat runs together in a chat session.
|
|
|
|
A chat run is a sequence of messages from the same sender.
|
|
|
|
Args:
|
|
chat_session: A chat session.
|
|
|
|
Returns:
|
|
A chat session with merged chat runs.
|
|
"""
|
|
messages: List[BaseMessage] = []
|
|
for message in chat_session["messages"]:
|
|
if not isinstance(message.content, str):
|
|
raise ValueError(
|
|
"Chat Loaders only support messages with content type string, "
|
|
f"got {message.content}"
|
|
)
|
|
if not messages:
|
|
messages.append(deepcopy(message))
|
|
elif (
|
|
isinstance(message, type(messages[-1]))
|
|
and messages[-1].additional_kwargs.get("sender") is not None
|
|
and messages[-1].additional_kwargs["sender"]
|
|
== message.additional_kwargs.get("sender")
|
|
):
|
|
if not isinstance(messages[-1].content, str):
|
|
raise ValueError(
|
|
"Chat Loaders only support messages with content type string, "
|
|
f"got {messages[-1].content}"
|
|
)
|
|
messages[-1].content = (
|
|
messages[-1].content + delimiter + message.content
|
|
).strip()
|
|
messages[-1].additional_kwargs.get("events", []).extend(
|
|
message.additional_kwargs.get("events") or []
|
|
)
|
|
else:
|
|
messages.append(deepcopy(message))
|
|
return ChatSession(messages=messages)
|
|
|
|
|
|
def merge_chat_runs(chat_sessions: Iterable[ChatSession]) -> Iterator[ChatSession]:
|
|
"""Merge chat runs together.
|
|
|
|
A chat run is a sequence of messages from the same sender.
|
|
|
|
Args:
|
|
chat_sessions: A list of chat sessions.
|
|
|
|
Returns:
|
|
A list of chat sessions with merged chat runs.
|
|
"""
|
|
for chat_session in chat_sessions:
|
|
yield merge_chat_runs_in_session(chat_session)
|
|
|
|
|
|
def map_ai_messages_in_session(chat_sessions: ChatSession, sender: str) -> ChatSession:
|
|
"""Convert messages from the specified 'sender' to AI messages.
|
|
|
|
This is useful for fine-tuning the AI to adapt to your voice.
|
|
"""
|
|
messages = []
|
|
num_converted = 0
|
|
for message in chat_sessions["messages"]:
|
|
if message.additional_kwargs.get("sender") == sender:
|
|
message = AIMessage(
|
|
content=message.content,
|
|
additional_kwargs=message.additional_kwargs.copy(),
|
|
example=getattr(message, "example", None), # type: ignore[arg-type]
|
|
)
|
|
num_converted += 1
|
|
messages.append(message)
|
|
return ChatSession(messages=messages)
|
|
|
|
|
|
def map_ai_messages(
|
|
chat_sessions: Iterable[ChatSession], sender: str
|
|
) -> Iterator[ChatSession]:
|
|
"""Convert messages from the specified 'sender' to AI messages.
|
|
|
|
This is useful for fine-tuning the AI to adapt to your voice.
|
|
"""
|
|
for chat_session in chat_sessions:
|
|
yield map_ai_messages_in_session(chat_session, sender)
|