yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2026-01-04 02:57:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix _debug info getting lost for previous nodes when using join nodes (#2776)

Browse Source 
* fix debug output for pipelines with join nodes

* add test

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
This commit is contained in:
tstadel 2022-07-07 15:10:13 +02:00 committed by GitHub
parent a766b70a8f
commit 45136badfe
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 40 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
haystack/pipelines/base.py
View File

@ -528,7 +528,11 @@ class Pipeline:
if queue.get(n): # concatenate inputs if it's a join node
existing_input = queue[n]
if "inputs" not in existing_input.keys():
updated_input: dict = {"inputs": [existing_input, node_output], "params": params}
updated_input: dict = {
"inputs": [existing_input, node_output],
"params": params,
"_debug": {**existing_input["_debug"], **node_output["_debug"]},
}
if query:
updated_input["query"] = query
if file_paths:

36
test/pipelines/test_pipeline_debug_and_validation.py
View File

@ -4,7 +4,7 @@ import json
import pytest
from haystack.pipelines import Pipeline, RootNode
from haystack.nodes import FARMReader, BM25Retriever
from haystack.nodes import FARMReader, BM25Retriever, JoinDocuments
from ..conftest import SAMPLES_PATH, MockRetriever as BaseMockRetriever, MockReader
@ -108,6 +108,40 @@ def test_debug_attributes_per_node(document_store_with_docs, tmp_path):
json.dumps(prediction, default=str)
@pytest.mark.elasticsearch
@pytest.mark.parametrize("document_store_with_docs", ["elasticsearch"], indirect=True)
def test_debug_attributes_for_join_nodes(document_store_with_docs, tmp_path):
es_retriever_1 = BM25Retriever(document_store=document_store_with_docs)
es_retriever_2 = BM25Retriever(document_store=document_store_with_docs)
pipeline = Pipeline()
pipeline.add_node(component=es_retriever_1, name="ESRetriever1", inputs=["Query"])
pipeline.add_node(component=es_retriever_2, name="ESRetriever2", inputs=["Query"])
pipeline.add_node(component=JoinDocuments(), name="JoinDocuments", inputs=["ESRetriever1", "ESRetriever2"])
prediction = pipeline.run(query="Who lives in Berlin?", debug=True)
assert "_debug" in prediction.keys()
assert "ESRetriever1" in prediction["_debug"].keys()
assert "ESRetriever2" in prediction["_debug"].keys()
assert "JoinDocuments" in prediction["_debug"].keys()
assert "input" in prediction["_debug"]["ESRetriever1"].keys()
assert "output" in prediction["_debug"]["ESRetriever1"].keys()
assert "input" in prediction["_debug"]["ESRetriever2"].keys()
assert "output" in prediction["_debug"]["ESRetriever2"].keys()
assert "input" in prediction["_debug"]["JoinDocuments"].keys()
assert "output" in prediction["_debug"]["JoinDocuments"].keys()
assert prediction["_debug"]["ESRetriever1"]["input"]
assert prediction["_debug"]["ESRetriever1"]["output"]
assert prediction["_debug"]["ESRetriever2"]["input"]
assert prediction["_debug"]["ESRetriever2"]["output"]
assert prediction["_debug"]["JoinDocuments"]["input"]
assert prediction["_debug"]["JoinDocuments"]["output"]
# Avoid circular reference: easiest way to detect those is to use json.dumps
json.dumps(prediction, default=str)
@pytest.mark.elasticsearch
@pytest.mark.parametrize("document_store_with_docs", ["elasticsearch"], indirect=True)
def test_global_debug_attributes_override_node_ones(document_store_with_docs, tmp_path):