SimpleKGPipeline problems

[apolo74]

Hi guys,
I attended your webinar on GraphRAG a couple of weeks ago and tried to implement your code but with no luck. I didn't want to use OpenAI since I want to develop my applications locally, privately, and completely offline if possible... so my first option has been to use Ollama models. I did a copy and paste of your code:

...
kg_builder_pdf = SimpleKGPipeline(
    llm             = llm,
    driver          = driver,
    text_splitter   = FixedSizeSplitter(chunk_size=500, chunk_overlap=100),
    embedder        = emb,
    entities        = node_labels,
    relations       = rel_types,
    prompt_template = prompt_template ,
    from_pdf        = True
)

pdf_file_paths = [
    'data/biomolecules-11-00928-v2-trunc.pdf',
    'data/GAP-between-patients-and-clinicians_2023_Best-Practice-trunc.pdf',
    'data/pgpm-13-39-trunc.pdf'
]

for path in pdf_file_paths:
    pdf_result = await kg_builder_pdf.run_async(file_path=path)

---

• Using OllamaLLM and OllamaEmbeddings:

from neo4j_graphrag.llm import OllamaLLM
from neo4j_graphrag.embeddings.ollama import OllamaEmbeddings

llm = OllamaLLM(model_name='llama3.2:3b')
emb = OllamaEmbeddings(model='snowflake-arctic-embed2')
...

I get the following error:

.venv\Lib\site-packages\pydantic\main.py", line 214, in init
validated_self = self.pydantic_validator.validate_python(data, self_instance=self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pydantic_core._pydantic_core.ValidationError: 1 validation error for Neo4jNode
embedding_properties.embedding.0
Input should be a valid number [type=float_type, input_value=[-0.021932466, 0.01252911...0.03033293, 0.014525634], input_type=list]
For further information, visit https://errors.pydantic.dev/2.10/v/float_type

---

• Using OpenAI and OpenAIEmbeddings:

from neo4j_graphrag.llm import OpenAILLM
from neo4j_graphrag.embeddings.openai import OpenAIEmbeddings

llm = OpenAILLM(
    model_name='gpt-4o-mini',
    model_params={
        'response-format': {'type': 'json_object'},
        'temperature': 0
    }
)
emb = OpenAIEmbeddings()
...

I get the following error:

.venv\Lib\site-packages\neo4j_graphrag\llm\openai_llm.py", line 138, in ainvoke
response = await self.async_client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\bduran\Documents\Coding\KnowledgeGraphs\Neo4j\graphRAG.venv\Lib\site-packages\openai_utils_utils.py", line 279, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
TypeError: AsyncCompletions.create() got an unexpected keyword argument 'response-format'

---

I'll appreciate any direction on how to implement a working graphRAG script, especially when using OllamaLLM and OllamaEmbeddings.
Thanks in advance,
Boris

[Dalididilo]

'response-format' Parameter is wrong replace with 'response_format'