Langchain & Deeplake: SelfQueryRetriever Error on querying code

[kaan9700]

I have a deeplake vector database with code chunks of a project. According to an issue I want to find the corresponding code chunks. For this I have written a SelfQueryRetriever.
But it throws an error exactly when I mention an expression like 'train.py script' in the query. If I leave this out, I get no error. The whole thing is supposed to work automatically for all possible issues, so it is not possible to simply say to keep such expressions out of the issues.

def CustomRetriever(files, dataset_path,issue):

    metadata_field_info = [
        AttributeInfo(
            name="source",
            description="The soruce file the chunk was extracted from",
            type="string",
        ),
        AttributeInfo(
            name="file_name",
            description="The name of the file the chunk was extracted from",
            type="string",
        ),
        AttributeInfo(
            name="chunk_id",
            description="the id of the chunk",
            type="string",
        ),
    ]
    document_content_description = "The sourcecode of a project"
    model = ChatOpenAI(model="gpt-4")

    embeddings = OpenAIEmbeddings(disallowed_special=())
    db = DeepLake(dataset_path=dataset_path, read_only=True, embedding=embeddings, exec_option='python')
    docs = (db.similarity_search(query=" ", k=10000000))
    retriever = SelfQueryRetriever.from_llm(
        model, db, document_content_description, metadata_field_info, verbose=True
    )
    try:
        # Ihr Code, der den Fehler verursacht
        print('TEST', retriever.get_relevant_documents(
            f"Which documents contain code to resolve the following issue? -> {issue}"))
    except ValueError as e:


        print(traceback.format_exc())

Here is the error:

query='CNN instead of BERT model in train.py script, handle data better, generated using Tensorflow, integrated into logic, adapted to word vectors, change code' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='source', value='train.py'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='file_name', value='train.py')]) limit=None

Traceback (most recent call last):
  File "/Users/kaanerbay/GitHub/Github_Issue_Solver/langchainLogic/retriever2.py", line 93, in CustomRetriever
    print('TEST', retriever.get_relevant_documents(
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/langchain/schema/retriever.py", line 208, in get_relevant_documents
    raise e
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/langchain/schema/retriever.py", line 201, in get_relevant_documents
    result = self._get_relevant_documents(
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/langchain/retrievers/self_query/base.py", line 135, in _get_relevant_documents
    docs = self.vectorstore.search(new_query, self.search_type, **search_kwargs)
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/langchain/vectorstores/base.py", line 121, in search
    return self.similarity_search(query, **kwargs)
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/langchain/vectorstores/deeplake.py", line 475, in similarity_search
    return self._search(
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/langchain/vectorstores/deeplake.py", line 348, in _search
    return self._search_tql(
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/langchain/vectorstores/deeplake.py", line 267, in _search_tql
    result = self.vectorstore.search(
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/deeplake/core/vectorstore/deeplake_vectorstore.py", line 429, in search
    utils.parse_search_args(
  File "/Users/kaanerbay/miniconda3/envs/main/lib/python3.10/site-packages/deeplake/core/vectorstore/vector_search/utils.py", line 229, in parse_search_args
    raise ValueError(
ValueError: User-specified TQL queries are not support for exec_option=python.

Here is the used issue:

a CNN should be used instead of the BERT model in the train.py script, because it can handle the type of data better.
The CNN should not be too complex, but also not too simple and should be generated using Tensorflow.
The CNN should be integrated into the logic and adapted according to the word vectors used. Change the code of it, as good as you can.