Error when Getting Started

[sutyum]

Not sure what I am doing wrong.

!pip install git+https://github.com/bclavie/RAGatouille.git

from ragatouille import RAGPretrainedModel

RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0")

I get the following error:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[7], line 1
----> 1 from ragatouille import RAGPretrainedModel
      3 RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0")

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/ragatouille/__init__.py:2
      1 __version__ = "0.0.4a4"
----> 2 from .RAGPretrainedModel import RAGPretrainedModel
      3 from .RAGTrainer import RAGTrainer
      5 __all__ = ["RAGPretrainedModel", "RAGTrainer"]

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/ragatouille/RAGPretrainedModel.py:7
      4 from langchain.retrievers.document_compressors.base import BaseDocumentCompressor
      5 from langchain_core.retrievers import BaseRetriever
----> 7 from ragatouille.data.corpus_processor import CorpusProcessor
      8 from ragatouille.data.preprocessors import llama_index_sentence_splitter
      9 from ragatouille.integrations import (
     10     RAGatouilleLangChainCompressor,
     11     RAGatouilleLangChainRetriever,
     12 )

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/ragatouille/data/__init__.py:1
----> 1 from .corpus_processor import CorpusProcessor
      2 from .preprocessors import llama_index_sentence_splitter
      3 from .training_data_processor import TrainingDataProcessor

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/ragatouille/data/corpus_processor.py:3
      1 from typing import Callable, Optional, Union
----> 3 from ragatouille.data.preprocessors import llama_index_sentence_splitter
      6 class CorpusProcessor:
      7     def __init__(
      8         self,
      9         document_splitter_fn: Optional[Callable] = llama_index_sentence_splitter,
     10         preprocessing_fn: Optional[Union[Callable, list[Callable]]] = None,
     11     ):

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/ragatouille/data/preprocessors.py:1
----> 1 from llama_index import Document
      2 from llama_index.text_splitter import SentenceSplitter
      5 def llama_index_sentence_splitter(documents: list[str], chunk_size=256):

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/__init__.py:21
     17 from llama_index.embeddings import OpenAIEmbedding
     19 # indices
     20 # loading
---> 21 from llama_index.indices import (
     22     ComposableGraph,
     23     DocumentSummaryIndex,
     24     GPTDocumentSummaryIndex,
     25     GPTKeywordTableIndex,
     26     GPTKnowledgeGraphIndex,
     27     GPTListIndex,
     28     GPTRAKEKeywordTableIndex,
     29     GPTSimpleKeywordTableIndex,
     30     GPTTreeIndex,
     31     GPTVectorStoreIndex,
     32     KeywordTableIndex,
     33     KnowledgeGraphIndex,
     34     ListIndex,
     35     RAKEKeywordTableIndex,
     36     SimpleKeywordTableIndex,
     37     SummaryIndex,
     38     TreeIndex,
     39     VectorStoreIndex,
     40     load_graph_from_storage,
     41     load_index_from_storage,
     42     load_indices_from_storage,
     43 )
     45 # structured
     46 from llama_index.indices.common.struct_store.base import SQLDocumentContextBuilder

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/indices/__init__.py:44
     39 from llama_index.indices.struct_store.sql import (
     40     GPTSQLStructStoreIndex,
     41     SQLStructStoreIndex,
     42 )
     43 from llama_index.indices.tree.base import GPTTreeIndex, TreeIndex
---> 44 from llama_index.indices.vector_store import GPTVectorStoreIndex, VectorStoreIndex
     46 __all__ = [
     47     "load_graph_from_storage",
     48     "load_index_from_storage",
   (...)
     78     "GPTEmptyIndex",
     79 ]

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/indices/vector_store/__init__.py:4
      1 """Vector-store based data structures."""
      3 from llama_index.indices.vector_store.base import GPTVectorStoreIndex, VectorStoreIndex
----> 4 from llama_index.indices.vector_store.retrievers import (
      5     VectorIndexAutoRetriever,
      6     VectorIndexRetriever,
      7 )
      9 __all__ = [
     10     "VectorStoreIndex",
     11     "VectorIndexRetriever",
   (...)
     14     "GPTVectorStoreIndex",
     15 ]

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/indices/vector_store/retrievers/__init__.py:4
      1 from llama_index.indices.vector_store.retrievers.retriever import (  # noqa: I001
      2     VectorIndexRetriever,
      3 )
----> 4 from llama_index.indices.vector_store.retrievers.auto_retriever import (
      5     VectorIndexAutoRetriever,
      6 )
      8 __all__ = [
      9     "VectorIndexRetriever",
     10     "VectorIndexAutoRetriever",
     11 ]

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/indices/vector_store/retrievers/auto_retriever/__init__.py:1
----> 1 from llama_index.indices.vector_store.retrievers.auto_retriever.auto_retriever import (
      2     VectorIndexAutoRetriever,
      3 )
      5 __all__ = [
      6     "VectorIndexAutoRetriever",
      7 ]

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/indices/vector_store/retrievers/auto_retriever/auto_retriever.py:11
      9 from llama_index.indices.vector_store.base import VectorStoreIndex
     10 from llama_index.indices.vector_store.retrievers import VectorIndexRetriever
---> 11 from llama_index.indices.vector_store.retrievers.auto_retriever.output_parser import (
     12     VectorStoreQueryOutputParser,
     13 )
     14 from llama_index.indices.vector_store.retrievers.auto_retriever.prompts import (
     15     DEFAULT_VECTOR_STORE_QUERY_PROMPT_TMPL,
     16 )
     17 from llama_index.output_parsers.base import OutputParserException, StructuredOutput

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/indices/vector_store/retrievers/auto_retriever/output_parser.py:3
      1 from typing import Any
----> 3 from llama_index.output_parsers.base import StructuredOutput
      4 from llama_index.output_parsers.utils import parse_json_markdown
      5 from llama_index.types import BaseOutputParser

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/output_parsers/__init__.py:3
      1 """Output parsers."""
----> 3 from llama_index.output_parsers.guardrails import GuardrailsOutputParser
      4 from llama_index.output_parsers.langchain import LangchainOutputParser
      5 from llama_index.output_parsers.pydantic import PydanticOutputParser

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/llama_index/output_parsers/guardrails.py:9
      6 from deprecated import deprecated
      8 try:
----> 9     from guardrails import Guard
     10 except ImportError:
     11     Guard = None

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/guardrails/__init__.py:3
      1 # Set up __init__.py so that users can do from guardrails import Response, Schema, etc.
----> 3 from guardrails.guard import Guard
      4 from guardrails.llm_providers import PromptCallable
      5 from guardrails.prompt import Instructions, Prompt

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/guardrails/guard.py:7
      3 from typing import Callable, Dict, Optional, Tuple, Union
      5 from eliot import start_action, to_file
----> 7 from guardrails.llm_providers import PromptCallable, get_llm_ask
      8 from guardrails.prompt import Instructions, Prompt
      9 from guardrails.rail import Rail

File ~/.pyenv/versions/3.10.9/lib/python3.10/site-packages/guardrails/llm_providers.py:16
     12 except ImportError:
     13     MANIFEST = False
     15 OPENAI_RETRYABLE_ERRORS = [
---> 16     openai.error.APIConnectionError,
     17     openai.error.APIError,
     18     openai.error.TryAgain,
     19     openai.error.Timeout,
     20     openai.error.RateLimitError,
     21     openai.error.ServiceUnavailableError,
     22 ]
     23 RETRYABLE_ERRORS = OPENAI_RETRYABLE_ERRORS
     26 class PromptCallableException(Exception):

AttributeError: module 'openai' has no attribute 'error'

---

I also tried with the version on pypi, had the same error.

---

OS: MacOS 14.1.1
Python: 3.10.9
Environment: VirtualEnv

[sutyum]

Setting up a new virtual environment solved the issue for me.