Error when converting docs to graph

[cakshat]

I am getting the following error when I am running the graph_documents = llm_transformer.convert_to_graph_documents(documents) line.

[/home/archaudh/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/IPython/core/interactiveshell.py:3577](https://file+.vscode-resource.vscode-cdn.net/home/archaudh/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/IPython/core/interactiveshell.py:3577): LangChainDeprecationWarning: As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. The langchain_core.pydantic_v1 module was a compatibility shim for pydantic v1, and should no longer be used. Please update the code to import from Pydantic directly.

For example, replace imports like: `from langchain_core.pydantic_v1 import BaseModel`
with: `from pydantic import BaseModel`
or the v1 compatibility namespace if you are working in a code base that has not been fully upgraded to pydantic 2 yet. 	from pydantic.v1 import BaseModel

  exec(code_obj, self.user_global_ns, self.user_ns)
True
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[5], line 8
      5     llm = ChatOpenAI(temperature=0, model="gpt-4o-mini")
      6 llm_transformer = LLMGraphTransformer(llm=llm)
----> 8 graph_documents = llm_transformer.convert_to_graph_documents(documents)

File [~/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/langchain_experimental/graph_transformers/llm.py:809](https://file+.vscode-resource.vscode-cdn.net/home/archaudh/research/GraphRAG-with-Llama-3.1/~/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/langchain_experimental/graph_transformers/llm.py:809), in LLMGraphTransformer.convert_to_graph_documents(self, documents, config)
    797 def convert_to_graph_documents(
    798     self, documents: Sequence[Document], config: Optional[RunnableConfig] = None
    799 ) -> List[GraphDocument]:
    800     """Convert a sequence of documents into graph documents.
    801 
    802     Args:
   (...)
    807         Sequence[GraphDocument]: The transformed documents as graphs.
    808     """
--> 809     return [self.process_response(document, config) for document in documents]

File [~/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/langchain_experimental/graph_transformers/llm.py:809](https://file+.vscode-resource.vscode-cdn.net/home/archaudh/research/GraphRAG-with-Llama-3.1/~/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/langchain_experimental/graph_transformers/llm.py:809), in (.0)
    797 def convert_to_graph_documents(
    798     self, documents: Sequence[Document], config: Optional[RunnableConfig] = None
    799 ) -> List[GraphDocument]:
    800     """Convert a sequence of documents into graph documents.
    801 
    802     Args:
   (...)
    807         Sequence[GraphDocument]: The transformed documents as graphs.
    808     """
--> 809     return [self.process_response(document, config) for document in documents]

File [~/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/langchain_experimental/graph_transformers/llm.py:754](https://file+.vscode-resource.vscode-cdn.net/home/archaudh/research/GraphRAG-with-Llama-3.1/~/anaconda3/envs/graphrag-tutorial/lib/python3.10/site-packages/langchain_experimental/graph_transformers/llm.py:754), in LLMGraphTransformer.process_response(self, document, config)
    750     parsed_json = [parsed_json]
    751 for rel in parsed_json:
    752     # Check if mandatory properties are there
    753     if (
--> 754         not rel.get("head")
    755         or not rel.get("tail")
    756         or not rel.get("relation")
    757     ):
    758         continue
    759     # Nodes need to be deduplicated using a set
    760     # Use default Node label for nodes if `missing`
AttributeError: 'list' object has no attribute 'get'

[kellerfabian]

same here. @cakshat did you find a solution?