relation "langchain_pg_collection" does not exist #5

New Issue

2026-02-16T05:16:02-05:00

yindo commented

2026-02-16 05:16:02 -05:00

Originally created by @joshpopelka20 on GitHub (Apr 22, 2024).

After creating the vector store,

vectorstore = PGVector(
    embeddings=embeddings,
    collection_name=collection_name,
    connection=connection,
    use_jsonb=True
)

I try to run:
vectorstore.add_documents(docs, ids=[doc.metadata['id'] for doc in docs])

I'm getting this error message: relation "langchain_pg_collection" does not exist

I'm using python3.10, psycopg3, and langchain-postgres v0.0.3

Originally created by @joshpopelka20 on GitHub (Apr 22, 2024). After creating the vector store, ``` vectorstore = PGVector( embeddings=embeddings, collection_name=collection_name, connection=connection, use_jsonb=True ) ``` I try to run: `vectorstore.add_documents(docs, ids=[doc.metadata['id'] for doc in docs])` I'm getting this error message: relation "langchain_pg_collection" does not exist I'm using python3.10, psycopg3, and langchain-postgres v0.0.3

yindo closed this issue

2026-02-16 05:16:02 -05:00

yindo commented

2026-02-16 05:16:02 -05:00

@joshpopelka20 commented on GitHub (Apr 23, 2024):

For anyone else facing this issue, I was able to figure it out by running these two commands after vectorstore.drop_tables():

vectorstore.create_tables_if_not_exists()
vectorstore.create_collection()

@joshpopelka20 commented on GitHub (Apr 23, 2024): For anyone else facing this issue, I was able to figure it out by running these two commands after vectorstore.drop_tables(): ``` vectorstore.create_tables_if_not_exists() vectorstore.create_collection() ```

yindo referenced this issue

2026-02-16 05:16:37 -05:00

[PR #5] [MERGED] Add docker-compose file #106

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: langchain-ai/langchain-postgres#5