Connected Chroma, chroma/sync-workspace fails #15

Closed
opened 2026-02-15 16:29:17 -05:00 by yindo · 5 comments
Owner

Originally created by @arnoldligtvoet on GitHub (Aug 3, 2023).

Installed in Docker and connected to local docker Chroma instance. Can see my Workspaces. Clicked on Workspace and then 'Sync Workspace Data'. This queues a job that failes.

Job response:
{
"canRetry": true,
"message": "Job failed with error",
"error": "Cannot read properties of null (reading 'title')",
"details": {}
}

Chroma 0.4.4

Originally created by @arnoldligtvoet on GitHub (Aug 3, 2023). Installed in Docker and connected to local docker Chroma instance. Can see my Workspaces. Clicked on Workspace and then 'Sync Workspace Data'. This queues a job that failes. Job response: { "canRetry": true, "message": "Job failed with error", "error": "Cannot read properties of null (reading 'title')", "details": {} } Chroma 0.4.4
yindo added the enhancementbug labels 2026-02-15 16:29:17 -05:00
yindo closed this issue 2026-02-15 16:29:17 -05:00
Author
Owner

@timothycarambat commented on GitHub (Aug 3, 2023):

How was this data embedded? That seems to indicate that it cannot find a document title for the embedding in the metadata. Tools like Llama Index and Langchain should attach the appropriate metadata

@timothycarambat commented on GitHub (Aug 3, 2023): How was this data embedded? That seems to indicate that it cannot find a document title for the embedding in the metadata. Tools like Llama Index and Langchain _should_ attach the appropriate metadata
Author
Owner

@arnoldligtvoet commented on GitHub (Aug 3, 2023):

The data was embedded using Chroma with a local embedder from NodeJS. There is no metadata with the embedding, just document and ids. So I connect from code to the ChromaDB, attach to a collection and insert documents.

Like so:
await collection.add({ ids: ["id1", "id2", "id3"], documents: ["lorem ipsum...", "doc2", "doc3"], })

@arnoldligtvoet commented on GitHub (Aug 3, 2023): The data was embedded using Chroma with a local embedder from NodeJS. There is no metadata with the embedding, just document and ids. So I connect from code to the ChromaDB, attach to a collection and insert documents. Like so: `await collection.add({ ids: ["id1", "id2", "id3"], documents: ["lorem ipsum...", "doc2", "doc3"], })`
Author
Owner

@arnoldligtvoet commented on GitHub (Aug 4, 2023):

Can confirm that rebuilding the collection with the metadatas: [{"title":"title"}] does work, although it does surprise me that this breaks the import of data, as it could use id instead of title if title is not present?

@arnoldligtvoet commented on GitHub (Aug 4, 2023): Can confirm that rebuilding the collection with the metadatas: [{"title":"title"}] does work, although it does surprise me that this breaks the import of data, as it could use id instead of title if title is not present?
Author
Owner

@timothycarambat commented on GitHub (Aug 4, 2023):

Can confirm that rebuilding the collection with the metadatas: [{"title":"title"}] does work, although it does surprise me that this breaks the import of data, as it could use id instead of title if title is not present?

Absolutely, will mark this as a bug because that's a very specific thing to expect. We will eventually not enforce any specific metadata at all and the table will be customizable to which columns you would want to display at all. Also add/update existing metadata fields as well

@timothycarambat commented on GitHub (Aug 4, 2023): > Can confirm that rebuilding the collection with the metadatas: [{"title":"title"}] does work, although it does surprise me that this breaks the import of data, as it could use id instead of title if title is not present? Absolutely, will mark this as a bug because that's a very specific thing to expect. We will eventually not enforce any specific metadata at all and the table will be customizable to which columns you would want to display at all. Also add/update existing metadata fields as well
Author
Owner

@timothycarambat commented on GitHub (Sep 14, 2023):

moved to #40

@timothycarambat commented on GitHub (Sep 14, 2023): moved to #40
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/vector-admin#15