c3c25db48c
- Use cases related to LLM call: https://cinnamon-ai.atlassian.net/browse/AUR-388?focusedCommentId=34873 - Sample usages: `test_llms_chat_models.py` and `test_llms_completion_models.py`: ```python from kotaemon.llms.chats.openai import AzureChatOpenAI model = AzureChatOpenAI( openai_api_base="https://test.openai.azure.com/", openai_api_key="some-key", openai_api_version="2023-03-15-preview", deployment_name="gpt35turbo", temperature=0, request_timeout=60, ) output = model("hello world") ``` For the LLM-call component, I decide to wrap around Langchain's LLM models and Langchain's Chat models. And set the interface as follow: - Completion LLM component: ```python class CompletionLLM: def run_raw(self, text: str) -> LLMInterface: # Run text completion: str in -> LLMInterface out def run_batch_raw(self, text: list[str]) -> list[LLMInterface]: # Run text completion in batch: list[str] in -> list[LLMInterface] out # run_document and run_batch_document just reuse run_raw and run_batch_raw, due to unclear use case ``` - Chat LLM component: ```python class ChatLLM: def run_raw(self, text: str) -> LLMInterface: # Run chat completion (no chat history): str in -> LLMInterface out def run_batch_raw(self, text: list[str]) -> list[LLMInterface]: # Run chat completion in batch mode (no chat history): list[str] in -> list[LLMInterface] out def run_document(self, text: list[BaseMessage]) -> LLMInterface: # Run chat completion (with chat history): list[langchain's BaseMessage] in -> LLMInterface out def run_batch_document(self, text: list[list[BaseMessage]]) -> list[LLMInterface]: # Run chat completion in batch mode (with chat history): list[list[langchain's BaseMessage]] in -> list[LLMInterface] out ``` - The LLMInterface is as follow: ```python @dataclass class LLMInterface: text: list[str] completion_tokens: int = -1 total_tokens: int = -1 prompt_tokens: int = -1 logits: list[list[float]] = field(default_factory=list) ```
51 lines
1.3 KiB
Python
51 lines
1.3 KiB
Python
import os
|
|
import sys
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def clean_artifacts_for_telemetry():
|
|
try:
|
|
del sys.modules["kotaemon"]
|
|
except KeyError:
|
|
pass
|
|
|
|
try:
|
|
del sys.modules["haystack"]
|
|
except KeyError:
|
|
pass
|
|
|
|
try:
|
|
del sys.modules["haystack.telemetry"]
|
|
except KeyError:
|
|
pass
|
|
|
|
if "HAYSTACK_TELEMETRY_ENABLED" in os.environ:
|
|
del os.environ["HAYSTACK_TELEMETRY_ENABLED"]
|
|
|
|
|
|
@pytest.mark.usefixtures("clean_artifacts_for_telemetry")
|
|
def test_disable_telemetry_import_haystack_first():
|
|
"""Test that telemetry is disabled when kotaemon lib is initiated after"""
|
|
import os
|
|
import haystack.telemetry
|
|
assert haystack.telemetry.telemetry is not None
|
|
assert os.environ.get("HAYSTACK_TELEMETRY_ENABLED", "True") != "False"
|
|
|
|
import kotaemon # noqa: F401
|
|
assert haystack.telemetry.telemetry is None
|
|
assert os.environ.get("HAYSTACK_TELEMETRY_ENABLED", "True") == "False"
|
|
|
|
|
|
@pytest.mark.usefixtures("clean_artifacts_for_telemetry")
|
|
def test_disable_telemetry_import_haystack_after_kotaemon():
|
|
"""Test that telemetry is disabled when kotaemon lib is initiated before"""
|
|
import os
|
|
|
|
import kotaemon # noqa: F401
|
|
import haystack.telemetry
|
|
assert haystack.telemetry.telemetry is None
|
|
assert os.environ.get("HAYSTACK_TELEMETRY_ENABLED", "True") == "False"
|
|
|