Hello trying the finetune embeddings

JJedi

Hello, trying the finetune embeddings tutorial here: https://gpt-index.readthedocs.io/en/stable/examples/finetuning/embeddings/finetune_embedding.html#

Running llama_index 0.8.28, using the ChatOpenAI llm, get the following AttributeError no attribute 'complete'. Should I be using a different version? Thanks for taking a look!

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[5], line 7
      6 llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0, openai_api_key=OPENAI_API_KEY)
----> 7 train_dataset = generate_qa_embedding_pairs(train_nodes, llm=llm)
      8 val_dataset = generate_qa_embedding_pairs(val_nodes, llm=llm)
     10 train_dataset.save_json("train_dataset.json")

File ~/.pyenv/versions/3.11.1/envs/llm-3.11.1/lib/python3.11/site-packages/llama_index/finetuning/embeddings/common.py:80, in generate_qa_embedding_pairs(nodes, llm, qa_generate_prompt_tmpl, num_questions_per_chunk)
     76 for node_id, text in tqdm(node_dict.items()):
     77     query = qa_generate_prompt_tmpl.format(
     78         context_str=text, num_questions_per_chunk=num_questions_per_chunk
     79     )
---> 80     response = llm.complete(query)
     82     result = str(response).strip().split("\n")
     83     questions = [
     84         re.sub(r"^\d+[\).\s]", "", question).strip() for question in result
     85     ]

AttributeError: 'ChatOpenAI' object has no attribute 'complete'

5 comments

TTeemu

Have you tried passing it with llm=OpenAI?

Plain Text

service_context = ServiceContext.from_defaults(callback_manager=callback_manager,
    llm=OpenAI(model="gpt-3.5-turbo-16k", temperature=0, max_tokens=1000), chunk_size=1024, node_parser=node_parser
)

JJedi

Looks to be similar error with OpenAI .

      7 llm = OpenAI(model="gpt-3.5-turbo", temperature=0, openai_api_key=OPENAI_API_KEY)
----> 9 train_dataset = generate_qa_embedding_pairs(train_nodes, llm=llm)
     10 val_dataset = generate_qa_embedding_pairs(val_nodes, llm=llm)
     12 train_dataset.save_json("train_dataset.json")

File ~/.pyenv/versions/3.11.1/envs/llm-3.11.1/lib/python3.11/site-packages/llama_index/finetuning/embeddings/common.py:80, in generate_qa_embedding_pairs(nodes, llm, qa_generate_prompt_tmpl, num_questions_per_chunk)
     76 for node_id, text in tqdm(node_dict.items()):
     77     query = qa_generate_prompt_tmpl.format(
     78         context_str=text, num_questions_per_chunk=num_questions_per_chunk
     79     )
---> 80     response = llm.complete(query)
     82     result = str(response).strip().split("\n")
     83     questions = [
     84         re.sub(r"^\d+[\).\s]", "", question).strip() for question in result
     85     ]

AttributeError: 'OpenAI' object has no attribute 'complete'

TTeemu

I'm not quite sure exactly what you're trying to do but have you looked at this documentation? https://gpt-index.readthedocs.io/en/stable/core_modules/model_modules/llms/root.html

LLogan M

Seems like you are using a LangChain LLM and not a LlamaIndex llm

Plain Text

from llama_index.llm import OpenAI

llm = OpenAI(model="gpt-3.5-turbo", temperature=0.1)

JJedi

yes, thank you both!

Add a reply

Find answers from the community

Hello trying the finetune embeddings