[Bug]: (#1296) KeyError: "Column(s) ['description_embedding'] do not exist"

[xxll88]

Do you need to file an issue?

• I have searched the existing issues and this bug is not already filed.
• My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
• I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the bug

After #1296：
when increment index update ， generate_text_embeddings(graphrag) ，show
/home/lile/graphrag/graphrag/index/update/entities.py:62 in _group_and_resolve_entities │
│ │
│ 59 │ # Group by name and resolve conflicts │
│ 60 │ aggregated = ( │
│ 61 │ │ combined.groupby("name") │
│ ❱ 62 │ │ .agg({ │
│ 63 │ │ │ "id": "first", │
│ 64 │ │ │ "type": "first", │
│ 65 │ │ │ "human_readable_id": "first",
KeyError: "Column(s) ['description_embedding'] do not exist"

Steps to reproduce

No response

Expected Behavior

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

• GraphRAG Version:
• Operating System:
• Python Version:
• Related Issues:

[AlonsoGuevara]

Hi @xxll88
We had a bug on main, but it has been already addressed in the preparion for release v0.4.0

If you pull from main or update your graphrag version the issue will no longer be there :)
Thanks for your report!

[huqianghui]

I have the same issu on Version: 0.4.1.
There is no description_embedding column in the final_entities.parque file.

[donaldNtjana]

loading 'create_final_entities.parquet' and creating description_embedding worked for me when doing 'local search'.

# Concatenate name and description for embedding
entity_embedding_df["name_description"] = (
    entity_embedding_df["name"] + ":" + entity_embedding_df["description"]
)

# Run embedding
entity_embedding_df["description_embedding"] = embed_text(entity_embedding_df["name_description"]) 

[ChengIC]

I have the same issues with 0.5.0

[joycerlz]

I have the same issue, i'm using 0.5.0 and was trying to load files to neo4j

[DanielGBabel]

Im having the same issue on the 1.0.0 version.

You guys removed the column description_embeddings

here is the index migration example

# We renamed "name" to "title" for consistency with the rest of the tables
if "name" in final_entities.columns:
    final_entities.rename(columns={"name": "title"}, inplace=True)
remove_columns(
    final_entities, ["mname_embedding", "graph_embedding", "description_embedding"]
)

and you have also renamed name for "title" now the neo4jgraph is not working properly

Please update this Neo4J guide notebook!

graphrag neo4j import cypher

[xiaomujiang]

Im having the same issue on the 1.1.2 version； Please update this Neo4J guide notebook!