unable to apply transformation: Connection error
Description:
I am trying to generate test set with ragas and I am getting connection error when invoking generator.generate_with_langchain_docs with the generator object. I am using llm proxy for the llm.
Ragas version: 2.0
Code to Reproduce #ignore un necessary imports below
pip install langchain-community import os !pip install ragas
from ragas.llms import LangchainLLMWrapper from ragas.embeddings import LangchainEmbeddingsWrapper from langchain_openai import ChatOpenAI from langchain_openai import OpenAIEmbeddings
from ragas.testset import TestsetGenerator from langchain_community.document_loaders import DirectoryLoader !pip install unstructured[local-inference]
pip install -qU langchain-huggingface from langchain_community.embeddings import HuggingFaceEmbeddings from sentence_transformers import SentenceTransformer from sentence_transformers.util import cos_sim from sentence_transformers.quantization import quantise_embeddings from langchain_community.embeddings import SentenceTransformerEmbeddings
from ragas.testset import TestsetGenerator from langchain.text_splitter import TokenTextSplitter
path = "/content" loader = DirectoryLoader(path, glob="**/*.txt") docs = loader.load()
embeddings = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
generator_llm_candy = ChatOpenAI(model_name = "gpt-4o", openai_api_base = "", openai_api_key = "", # DO NOT HARDCODE YOUR KEY model_kwargs = {'user': "" }) # DO NOT HARDCODE A USER HERE
generator_llm = LangchainLLMWrapper(generator_llm_candy) generator_embeddings = LangchainEmbeddingsWrapper(embeddings)
generator = TestsetGenerator(llm=generator_llm, embedding_model=generator_embeddings) dataset = generator.generate_with_langchain_docs(docs, testset_size=10)
data_frame = dataset.to_pandas()
data_frame.to_csv('file1.csv')
Error trace ERROR:ragas.testset.transforms.engine:unable to apply transformation: Connection error. ERROR:ragas.testset.transforms.engine:unable to apply transformation: 'headlines' property not found in this node ERROR:ragas.testset.transforms.engine:unable to apply transformation: Connection error. ERROR:ragas.testset.transforms.engine:unable to apply transformation: node.property('summary') must be a string, found '<class 'NoneType'>' ERROR:ragas.testset.transforms.engine:unable to apply transformation: Node c11e1996-b069-4197-a7dd-ba85818f1641 has no summary_embedding
I can see issue like this https://github.com/explodinggradients/ragas/issues/1496. But there the issue was not passing embedding model in the TestsetGenerator api but here in my code I do the both.