c6dd01e820
From pipeline > config > UI. Provide example project for promptui - Pipeline to config: `kotaemon.contribs.promptui.config.export_pipeline_to_config`. The config follows schema specified in this document: https://cinnamon-ai.atlassian.net/wiki/spaces/ATM/pages/2748711193/Technical+Detail. Note: this implementation exclude the logs, which will be handled in AUR-408. - Config to UI: `kotaemon.contribs.promptui.build_from_yaml` - Example project is located at `examples/promptui/`
67 lines
2.5 KiB
Python
67 lines
2.5 KiB
Python
import json
|
|
from pathlib import Path
|
|
from typing import cast
|
|
|
|
import pytest
|
|
from openai.api_resources.embedding import Embedding
|
|
|
|
from kotaemon.docstores import InMemoryDocumentStore
|
|
from kotaemon.documents.base import Document
|
|
from kotaemon.embeddings.openai import AzureOpenAIEmbeddings
|
|
from kotaemon.pipelines.indexing import IndexVectorStoreFromDocumentPipeline
|
|
from kotaemon.pipelines.retrieving import RetrieveDocumentFromVectorStorePipeline
|
|
from kotaemon.vectorstores import ChromaVectorStore
|
|
|
|
with open(Path(__file__).parent / "resources" / "embedding_openai.json") as f:
|
|
openai_embedding = json.load(f)
|
|
|
|
|
|
@pytest.fixture(scope="function")
|
|
def mock_openai_embedding(monkeypatch):
|
|
monkeypatch.setattr(Embedding, "create", lambda *args, **kwargs: openai_embedding)
|
|
|
|
|
|
def test_indexing(mock_openai_embedding, tmp_path):
|
|
db = ChromaVectorStore(path=str(tmp_path))
|
|
doc_store = InMemoryDocumentStore()
|
|
embedding = AzureOpenAIEmbeddings(
|
|
model="text-embedding-ada-002",
|
|
deployment="embedding-deployment",
|
|
openai_api_base="https://test.openai.azure.com/",
|
|
openai_api_key="some-key",
|
|
)
|
|
|
|
pipeline = IndexVectorStoreFromDocumentPipeline(
|
|
vector_store=db, embedding=embedding, doc_store=doc_store
|
|
)
|
|
pipeline.doc_store = cast(InMemoryDocumentStore, pipeline.doc_store)
|
|
assert pipeline.vector_store._collection.count() == 0, "Expected empty collection"
|
|
assert len(pipeline.doc_store._store) == 0, "Expected empty doc store"
|
|
pipeline(text=Document(text="Hello world"))
|
|
assert pipeline.vector_store._collection.count() == 1, "Index 1 item"
|
|
assert len(pipeline.doc_store._store) == 1, "Expected 1 document"
|
|
|
|
|
|
def test_retrieving(mock_openai_embedding, tmp_path):
|
|
db = ChromaVectorStore(path=str(tmp_path))
|
|
doc_store = InMemoryDocumentStore()
|
|
embedding = AzureOpenAIEmbeddings(
|
|
model="text-embedding-ada-002",
|
|
deployment="embedding-deployment",
|
|
openai_api_base="https://test.openai.azure.com/",
|
|
openai_api_key="some-key",
|
|
)
|
|
|
|
index_pipeline = IndexVectorStoreFromDocumentPipeline(
|
|
vector_store=db, embedding=embedding, doc_store=doc_store
|
|
)
|
|
retrieval_pipeline = RetrieveDocumentFromVectorStorePipeline(
|
|
vector_store=db, doc_store=doc_store, embedding=embedding
|
|
)
|
|
|
|
index_pipeline(text=Document(text="Hello world"))
|
|
output = retrieval_pipeline(text=["Hello world", "Hello world"])
|
|
|
|
assert len(output) == 2, "Expect 2 results"
|
|
assert output[0] == output[1], "Expect identical results"
|