Replies: 2 comments 19 replies
-
|
Beta Was this translation helpful? Give feedback.
-
|
Yes, you can add an extra column in the For example, if you want to add a new column named class EmbeddingStore(BaseModel):
"""Embedding store."""
__tablename__ = "langchain_pg_embedding"
collection_id = sqlalchemy.Column(
UUID(as_uuid=True),
sqlalchemy.ForeignKey(
f"{CollectionStore.__tablename__}.uuid",
ondelete="CASCADE",
),
)
collection = relationship(CollectionStore, back_populates="embeddings")
embedding = sqlalchemy.Column(sqlalchemy.ARRAY(sqlalchemy.REAL)) # type: ignore
document = sqlalchemy.Column(sqlalchemy.String, nullable=True)
cmetadata = sqlalchemy.Column(JSON, nullable=True)
# custom_id : any user defined id
custom_id = sqlalchemy.Column(sqlalchemy.String, nullable=True)
# Add the new column here
extra_column = sqlalchemy.Column(sqlalchemy.String, nullable=True)After adding the new column to the def create_tables_if_not_exists(self) -> None:
with self._conn.begin():
Base.metadata.create_all(self._conn)Finally, when adding embeddings, you can populate the new column as needed: def add_embeddings(
self,
texts: List[str],
embeddings: List[List[float]],
metadatas: List[dict],
ids: List[str],
extra_values: List[str], # Add a parameter for the new column values
**kwargs: Any,
) -> None:
with Session(self._conn) as session:
collection = self.get_collection(session)
if not collection:
raise ValueError("Collection not found")
for text, metadata, embedding, id, extra_value in zip(texts, metadatas, embeddings, ids, extra_values):
embedding_store = EmbeddingStore(
embedding=embedding,
document=text,
cmetadata=metadata,
custom_id=id,
extra_column=extra_value, # Populate the new column
)
collection.embeddings.append(embedding_store)
session.add(embedding_store)
session.commit()This way, you can add an extra column to the |
Beta Was this translation helpful? Give feedback.
-
|
@dosu |
Beta Was this translation helpful? Give feedback.
-
|
To call the
class EmbeddingStore(BaseModel):
"""Embedding store."""
__tablename__ = "langchain_pg_embedding"
collection_id = sqlalchemy.Column(
UUID(as_uuid=True),
sqlalchemy.ForeignKey(
f"{CollectionStore.__tablename__}.uuid",
ondelete="CASCADE",
),
)
collection = relationship(CollectionStore, back_populates="embeddings")
embedding = sqlalchemy.Column(sqlalchemy.ARRAY(sqlalchemy.REAL)) # type: ignore
document = sqlalchemy.Column(sqlalchemy.String, nullable=True)
cmetadata = sqlalchemy.Column(JSON, nullable=True)
custom_id = sqlalchemy.Column(sqlalchemy.String, nullable=True)
# New column
extra_column = sqlalchemy.Column(sqlalchemy.String, nullable=True)
def initialize_embedding_store_with_extra_column(connection_string: str, collection_name: str, extra_column_value: str):
# Initialize the PGEmbedding instance
embedding_function = Embeddings() # Replace with actual embedding function
pg_embedding = PGEmbedding(
connection_string=connection_string,
embedding_function=embedding_function,
collection_name=collection_name
)
# Add the new column value to the EmbeddingStore
with Session(pg_embedding._conn) as session:
collection = pg_embedding.get_collection(session)
if not collection:
raise ValueError("Collection not found")
# Example data
texts = ["example text"]
embeddings = [[0.1, 0.2, 0.3]] # Replace with actual embeddings
metadatas = [{}]
ids = [str(uuid.uuid4())]
for text, metadata, embedding, id in zip(texts, metadatas, embeddings, ids):
embedding_store = EmbeddingStore(
embedding=embedding,
document=text,
cmetadata=metadata,
custom_id=id,
extra_column=extra_column_value # Set the value for the new column
)
collection.embeddings.append(embedding_store)
session.add(embedding_store)
session.commit()In this example, the |
Beta Was this translation helpful? Give feedback.
-
class EmbeddingStore(BaseModel):
"""Embedding store."""
__tablename__ = "langchain_pg_embedding"
collection_id = sqlalchemy.Column(
UUID(as_uuid=True),
sqlalchemy.ForeignKey(
f"{CollectionStore.__tablename__}.uuid",
ondelete="CASCADE",
),
)
collection = relationship(CollectionStore, back_populates="embeddings")
embedding: Vector = sqlalchemy.Column(Vector(vector_dimension))
document = sqlalchemy.Column(sqlalchemy.String, nullable=True)
cmetadata = sqlalchemy.Column(JSON, nullable=True)
# custom_id : any user defined id
custom_id = sqlalchemy.Column(sqlalchemy.String, nullable=True)
_classes = (EmbeddingStore, CollectionStore)
return _classesdo i need to return _classes in the custom code you generated |
Beta Was this translation helpful? Give feedback.
-
|
No, you do not need to return |
Beta Was this translation helpful? Give feedback.
-
|
@dosu |
Beta Was this translation helpful? Give feedback.
-
|
@dosu [SQL: CREATE EXTENSION IF NOT EXISTS embedding] The above exception was the direct cause of the following exception: Traceback (most recent call last): [SQL: CREATE EXTENSION IF NOT EXISTS embedding] getting above error |
Beta Was this translation helpful? Give feedback.
-
|
The error you're encountering indicates that the PostgreSQL extension "embedding" is not installed on your system. To resolve this, you need to install the
After installing the necessary packages and creating the extension, you should be able to use the from langchain_community.vectorstores import PGEmbedding
# Example usage
connection_string = "your_postgres_connection_string"
embedding_function = YourEmbeddingFunction() # Replace with your embedding function
pg_embedding = PGEmbedding(connection_string=connection_string, embedding_function=embedding_function)If you continue to experience issues, make sure that the |
Beta Was this translation helpful? Give feedback.
-
|
@dosu ERROR: extension "embedding" is not available |
Beta Was this translation helpful? Give feedback.
-
|
To resolve the error "Could not open extension control file '/usr/share/postgresql/15/extension/embedding.control': No such file or directory," you need to install the
After following these steps, the |
Beta Was this translation helpful? Give feedback.
-
|
I am running it through docker |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Checked other resources
Commit to Help
Example Code
Description
I want to add an extra column in pgvector langchain_pg_embedding tables while embeddings process how can I ?
System Info
langchain==0.2.11
langchain-anthropic==0.1.22
langchain-community==0.2.10
langchain-core==0.2.26
langchain-openai==0.0.5
langchain-qdrant==0.1.3
langchain-text-splitters==0.2.2
langchain-weaviate==0.0.2
langchainhub==0.1.14
Linux
Python==3.12.4
Beta Was this translation helpful? Give feedback.
All reactions