Jedi

Hello trying the finetune embeddings

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

JJedi

Hi New to Llamaindex discord Running

Hi!, New to Llamaindex discord. Running into issues using LLMSingleSelector (running 0.8.8v). Code and a snip of trace below. Any help appreciated! thank you.

Plain Text

from llama_index.tools import ToolMetadata
from llama_index.selectors.llm_selectors import LLMSingleSelector


# choices as a list of tool metadata
choices = [
    ToolMetadata(description="I am choice 1", name="choice_1"),
    ToolMetadata(description="I am choice 2", name="choice_2"),
]

# choices as a list of strings
choices = ["choice 1 - description for choice 1", "choice 2: description for choice 2"]

selector = LLMSingleSelector.from_defaults()
selector_result = selector.select(choices, query="What choices do I have?")
print(selector_result.selections)

File ~/.pyenv/versions/llm-3.11.3/lib/python3.11/site-packages/llama_index/output_parsers/selection.py:56, in <listcomp>(.0)
54 if isinstance(json_output, dict):
55 json_output = [json_output]
---> 56 answers = [Answer.from_dict(json_dict) for json_dict in json_output]
57 return StructuredOutput(raw_output=output, parsed_output=answers)

File ~/.pyenv/versions/llm-3.11.3/lib/python3.11/site-packages/dataclasses_json/api.py:70, in DataClassJsonMixin.from_dict(cls, kvs, infer_missing)
65 @classmethod
66 def from_dict(cls: Type[A],
67 kvs: Json,
68 *,
69 infer_missing=False) -> A:
---> 70 return _decode_dataclass(cls, kvs, infer_missing)

File ~/.pyenv/versions/llm-3.11.3/lib/python3.11/site-packages/dataclasses_json/core.py:168, in _decode_dataclass(cls, kvs, infer_missing)
165 if not field.init:
166 continue
--> 168 field_value = kvs[field.name]
169 field_type = types[field.name]
170 if field_value is None:

KeyError: 'choice'

7 comments

JJedi

Hello, Trying correctness evaluator and

Hello, Trying correctness evaluator and hitting OpenAI API timeout errors. Anyone else has run into this? thanks for taking a look.

Plain Text

site-packages/llama_index/evaluation/correctness.py", line 134, in aevaluate
    eval_response = await self._service_context.llm.apredict(
....
site-packages/openai/_base_client.py", line 1442, in _request
    raise APITimeoutError(request=request) from err

7 comments

JJedi

Hello, what are some of the options

Hello, what are some of the options recommended for adding domain specific synonyms during embedding/retrieval in llamaindex workflow ? cc: @Logan M thanks!

2 comments

JJedi

hi trying to get a CustomQueryEngine

hi! trying to get a CustomQueryEngine going, following https://gpt-index.readthedocs.io/en/latest/examples/query_engine/custom_query_engine.html

How do I make the response streaming capable -- does the following look right? :

Plain Text

  
    def custom_query(self, query_str: str):
        logger.info(f"Triggering custom engine for query: {query_str}")
        response_gen = self.llm.stream_complete(
            qa_prompt
        )

        response= StreamingResponse(response_gen)
        return response

however, this creates following error upstream (integration with chainlit).

Plain Text

await response_message.stream_token(token=token)
TypeError: can only concatenate str (not "CompletionResponse") to str

Any help appreciated! thanks

3 comments

Find answers from the community

Hello trying the finetune embeddings

Hi New to Llamaindex discord Running

Hello, Trying correctness evaluator and

Hello, what are some of the options

hi trying to get a CustomQueryEngine