Python: Bug: vector store filters fail when the constant is on the left, including chained comparisons
I maintainer di solito rispondono entro 3 giorni
Valutazione
- Difficoltà
- 4/5
- Tempo stimato
- 3-5 giorni
- Idoneità per principianti
- 35/100
- Tipo di issue
- Bug
- Chiarezza
- Abbastanza chiara
- Stato di attività
- Ferma
- Stack tecnologico
- python
- Ambito
- backend-api-design, databases
Direzione di ricerca
Start in Python’s VectorSearch._build_filter and read _FoldUnaryNumericConstants from the referenced change #14572; compare it with the filter parsers for Qdrant and Chroma. The issue proposes normalizing reversed and chained comparisons before connector parsing. Done means the three examples return the expected records on Qdrant and Chroma while existing field-left filters continue to work; an open linked pull request (#14781) indicates work is already underway.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Describe the bug
Vector store filters fail when the constant is on the left of a comparison, and that includes Python's chained range comparison. QdrantCollection and ChromaCollection raise for all three of these, while InMemoryCollection and FaissCollection return the expected records:
await collection.search(vector=[1.0, 1.0], filter="lambda x: 2 < x.num") # expected num 3, 4, 5
await collection.search(vector=[1.0, 1.0], filter="lambda x: 3 == x.num") # expected num 3
await collection.search(vector=[1.0, 1.0], filter="lambda x: 1 <= x.num < 4") # expected num 1, 2, 3
Qdrant fails with a pydantic ValidationError (FieldCondition gets key=3, or Range gets lt="num"). Chroma fails with Expected where key to be a str, got 2.
The chained form is the one users are most likely to write. QdrantCollection._lambda_parser already splits chains into an AND (the comment there gives 1 < x < 3 as the example), but the first pair of a chain always has the constant on the left, so that path can't succeed today.
To Reproduce
A record type with an int data field num, six records with num 0 to 5, then the searches above on QdrantCollection(location=":memory:") and an ephemeral ChromaCollection. Rewriting each filter with the field on the left (x.num > 2, x.num >= 1 and x.num < 4) works on both.
Expected behavior
The same records as the field-on-the-left form, as InMemoryCollection returns today.
Additional context
Checked by running: Qdrant and Chroma fail. In-memory and FAISS work.
Read in the code but not run: the Weaviate, Pinecone, MongoDB and Azure Cosmos DB parsers also take the left operand as the field name and have no case for a constant there. Redis and Azure AI Search handle the reversed form explicitly. The SQL-based connectors may work by accident, since 2 < num is valid SQL.
Suggested fix: Normalize the tree once in VectorSearch._build_filter, next to _FoldUnaryNumericConstants from #14572, so the connector parsers stay unchanged:
- rewrite
Constant op FieldasField op' Constant, flipping</>and<=/>=and keeping==/!= - split a chained comparison
a < b < cintoa < b and b < c
in and not in with the constant on the left mean "the list field contains the value", which is a different operation, so I'd leave them as they are.
I'm happy to open a PR for this if the approach sounds right.
Platform
- Language: Python
- Source: main at b714e97
- Python 3.12, qdrant-client 1.20.0, chromadb 1.5.9
AI disclosure: found with Claude Code while comparing filter results across the Python connectors.
- Lingua principale
- C#
- Stelle
- 28.8k
- Fork
- 4.9k
- Merge medio
- 2g 17h
- PR unite (30g)
- 48
Preparare l'ambiente
Avvia il container di sviluppo del progetto nel browser, con il tuo account GitHub.
- Nessun Dockerfile né file Docker Compose
- Ha un modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di microsoft/semantic-kernel
-
Python: Bug: ChatMessageContent.from_element drops AudioContent and BinaryContent into raw TextContentForse già presa @halcyon-past l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 75/100
microsoft/semantic-kernel#14824 · 1 commento ·
I maintainer di solito rispondono entro 3 giorni
-
Python: Bug: Redis search returns None for every field that declares a storage_name, because RETURN lists the declared nameForse già presa @wasim-builds l’ha presa 9 giorni fa. Apertapython triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
microsoft/semantic-kernel#14753 · 1 commento ·
I maintainer di solito rispondono entro 3 giorni
-
.Net: gpt-image-1 is the default image model in the .NET OpenAI connector, and OpenAI shuts it down on October 23Forse già presa @nightcityblade l’ha presa 46 giorni fa. Aperta.NET triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 73/100
microsoft/semantic-kernel#14526 · 1 commento ·
I maintainer di solito rispondono entro 3 giorni
-
Python: VolatileMemoryStore.get_batch and get_nearest_matches ignore with_embeddings=False (deepcopy result is discarded)Forse già presa @VANDRANKI l’ha presa 48 giorni fa. Apertapython triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 84/100
microsoft/semantic-kernel#14522 ·
I maintainer di solito rispondono entro 3 giorni
-
.Net: Bug: BinaryContent does not decode the %xx escapes of a non-base64 data URIForse già presa @Laurianti l’ha presa 48 giorni fa. Aperta.NET triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
microsoft/semantic-kernel#14518 ·
I maintainer di solito rispondono entro 3 giorni
Tutte le issue di microsoft/semantic-kernel
Issue simili
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 75/100
I maintainer di solito rispondono entro 1 giorno
-
Support Flux ignore rules (drift detection ignore paths) in Microsoft.KubernetesConfiguration schemaAperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 65/100
Azure/azure-resource-manager-schemas#3921 ·
I maintainer di solito rispondono entro 1 giorno
-
text-align: justify is ignored in HTML to PDF conversionForse già presa @PrzemyslawKlys l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 78/100
I maintainer di solito rispondono entro 4 giorni
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 75/100
asyncapi/modelina#2709 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno