quivr/core/tests/conftest.py
Jacopo Chevallard 285fe5b960
feat: websearch, tool use, user intent, dynamic retrieval, multiple questions (#3424)
# Description

This PR includes far too many new features:

- detection of user intent (closes CORE-211)
- treating multiple questions in parallel (closes CORE-212)
- using the chat history when answering a question (closes CORE-213)
- filtering of retrieved chunks by relevance threshold (closes CORE-217)
- dynamic retrieval of chunks (closes CORE-218)
- enabling web search via Tavily (closes CORE-220)
- enabling agent / assistant to activate tools when relevant to complete
the user task (closes CORE-224)

Also closes CORE-205

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):

---------

Co-authored-by: Stan Girard <stan@quivr.app>
2024-10-31 17:57:54 +01:00

92 lines
3.0 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import json
import os
from pathlib import Path
from uuid import uuid4
import pytest
from langchain_core.embeddings import DeterministicFakeEmbedding
from langchain_core.language_models import FakeListChatModel
from langchain_core.messages.ai import AIMessageChunk
from langchain_core.runnables.utils import AddableDict
from langchain_core.vectorstores import InMemoryVectorStore
from quivr_core.rag.entities.config import LLMEndpointConfig
from quivr_core.files.file import FileExtension, QuivrFile
from quivr_core.llm import LLMEndpoint
@pytest.fixture(scope="function")
def temp_data_file(tmp_path):
data = "This is some test data."
temp_file = tmp_path / "data.txt"
temp_file.write_text(data)
return temp_file
@pytest.fixture(scope="function")
def quivr_txt(temp_data_file):
return QuivrFile(
id=uuid4(),
brain_id=uuid4(),
original_filename=temp_data_file.name,
path=temp_data_file,
file_extension=FileExtension.txt,
file_sha1="123",
)
@pytest.fixture
def quivr_pdf():
return QuivrFile(
id=uuid4(),
brain_id=uuid4(),
original_filename="dummy.pdf",
path=Path("./tests/processor/data/dummy.pdf"),
file_extension=FileExtension.pdf,
file_sha1="13bh234jh234",
)
@pytest.fixture
def full_response():
return "Natural Language Processing (NLP) is a field of artificial intelligence that focuses on the interaction between computers and humans through natural language. The ultimate objective of NLP is to enable computers to understand, interpret, and respond to human language in a way that is both valuable and meaningful. NLP combines computational linguistics—rule-based modeling of human language—with statistical, machine learning, and deep learning models. This combination allows computers to process human language in the form of text or voice data and to understand its full meaning, complete with the speaker or writers intent and sentiment. Key tasks in NLP include text and speech recognition, translation, sentiment analysis, and topic segmentation."
@pytest.fixture
def chunks_stream_answer():
with open("./tests/chunk_stream_fixture.jsonl", "r") as f:
raw_chunks = list(f)
chunks = []
for rc in raw_chunks:
chunk = AddableDict(**json.loads(rc))
if "answer" in chunk:
chunk["answer"] = AIMessageChunk(**chunk["answer"])
chunks.append(chunk)
return chunks
@pytest.fixture(autouse=True)
def openai_api_key():
os.environ["OPENAI_API_KEY"] = "this-is-a-test-key"
@pytest.fixture
def answers():
return [f"answer_{i}" for i in range(10)]
@pytest.fixture(scope="function")
def fake_llm(answers: list[str]):
llm = FakeListChatModel(responses=answers)
return LLMEndpoint(llm=llm, llm_config=LLMEndpointConfig(model="fake_model"))
@pytest.fixture(scope="function")
def embedder():
return DeterministicFakeEmbedding(size=20)
@pytest.fixture(scope="function")
def mem_vector_store(embedder):
return InMemoryVectorStore(embedder)