mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-18 09:01:03 +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()
```
143 lines
5.1 KiB
Python
143 lines
5.1 KiB
Python
"""Test OllamaFunctions"""
|
|
|
|
import unittest
|
|
|
|
from langchain_community.tools import DuckDuckGoSearchResults
|
|
from langchain_community.tools.pubmed.tool import PubmedQueryRun
|
|
from langchain_core.messages import AIMessage
|
|
from langchain_core.pydantic_v1 import BaseModel, Field
|
|
|
|
from langchain_experimental.llms.ollama_functions import (
|
|
OllamaFunctions,
|
|
convert_to_ollama_tool,
|
|
)
|
|
|
|
|
|
class Joke(BaseModel):
|
|
setup: str = Field(description="The setup of the joke")
|
|
punchline: str = Field(description="The punchline to the joke")
|
|
|
|
|
|
class TestOllamaFunctions(unittest.TestCase):
|
|
"""
|
|
Test OllamaFunctions
|
|
"""
|
|
|
|
def test_default_ollama_functions(self) -> None:
|
|
base_model = OllamaFunctions(model="phi3", format="json")
|
|
|
|
# bind functions
|
|
model = base_model.bind_tools(
|
|
tools=[
|
|
{
|
|
"name": "get_current_weather",
|
|
"description": "Get the current weather in a given location",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"location": {
|
|
"type": "string",
|
|
"description": "The city and state, "
|
|
"e.g. San Francisco, CA",
|
|
},
|
|
"unit": {
|
|
"type": "string",
|
|
"enum": ["celsius", "fahrenheit"],
|
|
},
|
|
},
|
|
"required": ["location"],
|
|
},
|
|
}
|
|
],
|
|
function_call={"name": "get_current_weather"},
|
|
)
|
|
|
|
res = model.invoke("What's the weather in San Francisco?")
|
|
|
|
self.assertIsInstance(res, AIMessage)
|
|
res = AIMessage(**res.__dict__)
|
|
tool_calls = res.tool_calls
|
|
assert tool_calls
|
|
tool_call = tool_calls[0]
|
|
assert tool_call
|
|
self.assertEqual("get_current_weather", tool_call.get("name"))
|
|
|
|
def test_ollama_functions_tools(self) -> None:
|
|
base_model = OllamaFunctions(model="phi3", format="json")
|
|
model = base_model.bind_tools(
|
|
tools=[PubmedQueryRun(), DuckDuckGoSearchResults(max_results=2)] # type: ignore[call-arg]
|
|
)
|
|
res = model.invoke("What causes lung cancer?")
|
|
self.assertIsInstance(res, AIMessage)
|
|
res = AIMessage(**res.__dict__)
|
|
tool_calls = res.tool_calls
|
|
assert tool_calls
|
|
tool_call = tool_calls[0]
|
|
assert tool_call
|
|
self.assertEqual("pub_med", tool_call.get("name"))
|
|
|
|
def test_default_ollama_functions_default_response(self) -> None:
|
|
base_model = OllamaFunctions(model="phi3", format="json")
|
|
|
|
# bind functions
|
|
model = base_model.bind_tools(
|
|
tools=[
|
|
{
|
|
"name": "get_current_weather",
|
|
"description": "Get the current weather in a given location",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"location": {
|
|
"type": "string",
|
|
"description": "The city and state, "
|
|
"e.g. San Francisco, CA",
|
|
},
|
|
"unit": {
|
|
"type": "string",
|
|
"enum": ["celsius", "fahrenheit"],
|
|
},
|
|
},
|
|
"required": ["location"],
|
|
},
|
|
}
|
|
]
|
|
)
|
|
|
|
res = model.invoke("What is the capital of France?")
|
|
|
|
self.assertIsInstance(res, AIMessage)
|
|
res = AIMessage(**res.__dict__)
|
|
tool_calls = res.tool_calls
|
|
if len(tool_calls) > 0:
|
|
tool_call = tool_calls[0]
|
|
assert tool_call
|
|
self.assertEqual("__conversational_response", tool_call.get("name"))
|
|
|
|
def test_ollama_structured_output(self) -> None:
|
|
model = OllamaFunctions(model="phi3")
|
|
structured_llm = model.with_structured_output(Joke, include_raw=False)
|
|
|
|
res = structured_llm.invoke("Tell me a joke about cats")
|
|
assert isinstance(res, Joke)
|
|
|
|
def test_ollama_structured_output_with_json(self) -> None:
|
|
model = OllamaFunctions(model="phi3")
|
|
joke_schema = convert_to_ollama_tool(Joke)
|
|
structured_llm = model.with_structured_output(joke_schema, include_raw=False)
|
|
|
|
res = structured_llm.invoke("Tell me a joke about cats")
|
|
assert "setup" in res
|
|
assert "punchline" in res
|
|
|
|
def test_ollama_structured_output_raw(self) -> None:
|
|
model = OllamaFunctions(model="phi3")
|
|
structured_llm = model.with_structured_output(Joke, include_raw=True)
|
|
|
|
res = structured_llm.invoke("Tell me a joke about cars")
|
|
assert isinstance(res, dict)
|
|
assert "raw" in res
|
|
assert "parsed" in res
|
|
assert isinstance(res["raw"], AIMessage)
|
|
assert isinstance(res["parsed"], Joke)
|