Skip to content

fix: discard metadata fields if not set in Weaviate#3578

Merged
masci merged 2 commits intomainfrom
massi/weaviate-bug
Nov 15, 2022
Merged

fix: discard metadata fields if not set in Weaviate#3578
masci merged 2 commits intomainfrom
massi/weaviate-bug

Conversation

@masci
Copy link
Contributor

@masci masci commented Nov 15, 2022

Related Issues

Weaviate hardcodes certain metadata fields into its index, in this case name. When name is not present in the original document, and only if other metadata is set, after one full roundtrip write/read you end up having meta["name"] == None in the resulting doc.

Proposed Changes:

  • Drop the name field from meta if its value is None

How did you test it?

pytest -m"document_store and integration" test/document_stores/test_weaviate.py -x -vv

Notes for the reviewer

While running the tests, another bug was exposed: the embedding field in Document was set regardless of the return_embeddings init param - this is fixed now.

I also noticed the original documents passed to write_documents are modified when they don't contain embeddings, which I think it's wrong but I guess that goes for another time.

Checklist

@masci masci added type:bug Something isn't working topic:weaviate labels Nov 15, 2022
@masci masci requested a review from a team as a code owner November 15, 2022 11:12
@masci masci requested review from bogdankostic and removed request for a team November 15, 2022 11:12
@julian-risch julian-risch mentioned this pull request Nov 15, 2022
Merged
6 tasks
bogdankostic
bogdankostic requested changes Nov 15, 2022
View reviewed changes
Copy link
Contributor

@bogdankostic bogdankostic left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added one comment wrt to how we check whether to include a metadata field.

@bogdankostic
Copy link
Contributor

bogdankostic commented Nov 15, 2022

I also noticed the original documents passed to write_documents are modified when they don't contain embeddings, which I think it's wrong but I guess that goes for another time.

I think we do this because Weaviate requires Documents to contain embeddings in order to index them. (At least this was the case at the time we added WeaviateDocumentStore to Haystack if I recall correctly.)

@masci masci requested a review from bogdankostic November 15, 2022 17:00
bogdankostic
bogdankostic approved these changes Nov 15, 2022
View reviewed changes
Copy link
Contributor

@bogdankostic bogdankostic left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, cool that you directly fixed the bug about return_embeddings! :)

@masci masci mentioned this pull request Nov 15, 2022
Merged
6 tasks
@masci masci merged commit ba75d39 into main Nov 15, 2022
@masci masci deleted the massi/weaviate-bug branch November 15, 2022 21:02
ZanSara added a commit that referenced this pull request Nov 28, 2022
@brandenchan @masci
@github-actions @anakin87 @julian-risch @ZanSara @espoirMur @TuanaCelik @tstadel
docs: Reformat code blocks in docstrings (#3580)
4a83b20 
* Fix docstrings for DocumentStores

* Fix docstrings for AnswerGenerator

* Fix docstrings for Connector

* Fix docstrings for DocumentClassifier

* Fix docstrings for LabelGenerator

* Fix docstrings for QueryClassifier

* Fix docstrings for Ranker

* Fix docstrings for Retriever and Summarizer

* Fix docstrings for Translator

* Fix docstrings for Pipelines

* Fix docstrings for Primitives

* Fix Python code block spacing

* Add line break before code block

* Fix code blocks

* fix: discard metadata fields if not set in Weaviate (#3578)

* fix weaviate bug in returning embeddings and setting empty meta fields

* review comment

* Update unstable version and openapi schema (#3584)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* fix: Flatten `DocumentClassifier` output in `SQLDocumentStore`; remove `_sql_session_rollback` hack in tests (#3273)

* first draft

* fix

* fix

* move test to test_sql

* test: add test to check id_hash_keys is not ignored (#3577)

* refactor: Generate JSON schema when missing (#3533)

* removed unused script

* print info logs when generating openapi schema

* create json schema only when needed

* fix tests

* Remove leftover

Co-authored-by: ZanSara <sarazanzo94@gmail.com>

* move milvus tests to their own module (#3596)

* feat: store metadata using JSON in SQLDocumentStore (#3547)

* add warnings

* make the field cachable

* review comment

* Pin faiss-cpu as 1.7.3 seems to have problems (#3603)

* Update Haystack imports (#3599)

* Update Python version (#3602)

* fix: `ParsrConverter` fails on pages without text (#3605)

* try to fix bug

* remove print

* leftover

* refactor: update Squad data  (#3513)

* refractor the to_squad data class

* fix the validation label

* refractor the to_squad data class

* fix the validation label

* add the test for the to_label object function

* fix the tests for to_label_objects

* move all the test related to squad data to one file

* remove unused imports

* revert tiny_augmented.json

Co-authored-by: ZanSara <sarazanzo94@gmail.com>

* Url fixes (#3592)

* add 2 example scripts

* fixing faq script

* fixing some urls

* removing example scripts

* black reformatting

* add labeler to the repo (#3609)

* convert eval metrics to python float (#3612)

* feat: add support for `BM25Retriever` in `InMemoryDocumentStore` (#3561)

* very first draft

* implement query and query_batch

* add more bm25 parameters

* add rank_bm25 dependency

* fix mypy

* remove tokenizer callable parameter

* remove unused import

* only json serializable attributes

* try to fix: pylint too-many-public-methods / R0904

* bm25 attribute always present

* convert errors into warnings to make the tutorial 1 work

* add docstrings; tests

* try to make tests run

* better docstrings; revert not running tests

* some suggestions from review

* rename elasticsearch retriever as bm25 in tests; try to test memory_bm25

* exclude tests with filters

* change elasticsearch to bm25 retriever in test_summarizer

* add tests

* try to improve tests

* better type hint

* adapt test_table_text_retriever_embedding

* handle non-textual docs

* query only textual documents

* Incorporate Reviewer feedback

* refactor: replace `torch.no_grad` with `torch.inference_mode` (where possible) (#3601)

* try to replace torch.no_grad

* revert erroneous change

* revert other module breaking

* revert training/base

* Fix docstrings for DocumentStores

* Fix docstrings for AnswerGenerator

* Fix docstrings for Connector

* Fix docstrings for DocumentClassifier

* Fix docstrings for LabelGenerator

* Fix docstrings for QueryClassifier

* Fix docstrings for Ranker

* Fix docstrings for Retriever and Summarizer

* Fix docstrings for Translator

* Fix docstrings for Pipelines

* Fix docstrings for Primitives

* Fix Python code block spacing

* Add line break before code block

* Fix code blocks

* Incorporate Reviewer feedback

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
Co-authored-by: ZanSara <sarazanzo94@gmail.com>
Co-authored-by: Espoir Murhabazi <espoir.mur@gmail.com>
Co-authored-by: Tuana Celik <tuana.celik@deepset.ai>
Co-authored-by: tstadel <60758086+tstadel@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@bogdankostic bogdankostic bogdankostic approved these changes

Assignees

No one assigned

Labels

topic:weaviate type:bug Something isn't working

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@masci @bogdankostic