mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-09-07 15:23:31 +00:00
f13443054a
* Adding dummy generator implementation * Adding tutorial to try the model * Committing current non working code * Committing current update where we need to call generate function directly and need to convert embedding to tensor way * Addressing review comments. * Refactoring finder, and implementing rag_generator class. * Refined the implementation of RAGGenerator and now it is in clean shape * Renaming RAGGenerator to RAGenerator * Reverting change from finder.py and addressing review comments * Remove support for RagSequenceForGeneration * Utilizing embed_passage function from DensePassageRetriever * Adding sample test data to verify generator output * Updating testing script * Updating testing script * Fixing bug related to top_k * Updating latest farm dependency * Comment out farm dependency * Reverting changes from TransformersReader * Adding transformers dataset to compare transformers and haystack generator implementation * Using generator_encoder instead of question_encoder to generate context_input_ids * Adding workaround to install FARM dependency from master branch * Removing unnecessary changes * Fixing generator test * Removing transformers datasets * Fixing generator test * Some cleanup and updating TODO comments * Adding tutorial notebook * Updating tutorials with comments * Explicitly passing token model in RAG test * Addressing review comments * Fixing notebook * Refactoring tests to reduce memory footprint * Split generator tests in separate ci step and before running it reclaim memory by terminating containers * Moving tika dependent test to separate dir * Remove unwanted code * Brining reader under session scope * Farm is now session object hence restoring changes from default value * Updating assert for pdf converter * Dummy commit to trigger CI flow * REducing memory footprint required for generator tests * Fixing mypy issues * Marking test with tika and elasticsearch markers. Reverting changes in CI and pytest splits * reducing changes * Fixing CI * changing elastic search ci * Fixing test error * Disabling return of embedding * Marking generator test as well * Refactoring tutorials * Increasing ES memory to 750M * Trying another fix for ES CI * Reverting CI changes * Splitting tests in CI * Generator and non-generator markers split * Adding pytest.ini to add markers and enable strict-markers option * Reducing elastic search container memory * Simplifying generator test by using documents with embedding directly * Bump up farm to 0.5.0
36 lines
1.7 KiB
Python
36 lines
1.7 KiB
Python
import pytest
|
|
|
|
|
|
@pytest.mark.elasticsearch
|
|
@pytest.mark.parametrize("document_store_with_docs", [("elasticsearch")], indirect=True)
|
|
@pytest.mark.parametrize("retriever_with_docs", ["elasticsearch"], indirect=True)
|
|
def test_elasticsearch_retrieval(retriever_with_docs, document_store_with_docs):
|
|
res = retriever_with_docs.retrieve(query="Who lives in Berlin?")
|
|
assert res[0].text == "My name is Carla and I live in Berlin"
|
|
assert len(res) == 3
|
|
assert res[0].meta["name"] == "filename1"
|
|
|
|
|
|
@pytest.mark.elasticsearch
|
|
@pytest.mark.parametrize("document_store_with_docs", [("elasticsearch")], indirect=True)
|
|
@pytest.mark.parametrize("retriever_with_docs", ["elasticsearch"], indirect=True)
|
|
def test_elasticsearch_retrieval_filters(retriever_with_docs, document_store_with_docs):
|
|
res = retriever_with_docs.retrieve(query="Who lives in Berlin?", filters={"name": ["filename1"]})
|
|
assert res[0].text == "My name is Carla and I live in Berlin"
|
|
assert len(res) == 1
|
|
assert res[0].meta["name"] == "filename1"
|
|
|
|
res = retriever_with_docs.retrieve(query="Who lives in Berlin?", filters={"name":["filename1"], "meta_field": ["not_existing_value"]})
|
|
assert len(res) == 0
|
|
|
|
res = retriever_with_docs.retrieve(query="Who lives in Berlin?", filters={"name":["filename1"], "not_existing_field": ["not_existing_value"]})
|
|
assert len(res) == 0
|
|
|
|
res = retriever_with_docs.retrieve(query="Who lives in Berlin?", filters={"name":["filename1"], "meta_field": ["test1","test2"]})
|
|
assert res[0].text == "My name is Carla and I live in Berlin"
|
|
assert len(res) == 1
|
|
assert res[0].meta["name"] == "filename1"
|
|
|
|
res = retriever_with_docs.retrieve(query="Who lives in Berlin?", filters={"name":["filename1"], "meta_field":["test2"]})
|
|
assert len(res) == 0
|