vision_service-1        | pydantic_core._pydantic_core.ValidationError: 2 validation errors for ChatMessage
vision_service-1        | blocks.0
vision_service-1        |   Unable to extract tag using discriminator ‘block_type’ [type=union_tag_not_found, input_value={‘type’: ‘text’, ‘text’: ‘Describe what you see’}, input_type=dict]
vision_service-1        |     For further information visit https://errors.pydantic.dev/2.9/v/union_tag_not_found
vision_service-1        | blocks.1
vision_service-1        |   Unable to extract tag using discriminator ‘block_type’ [type=union_tag_not_found, input_value={‘type’: ‘image_url’, ‘im...gg==’, ‘detail’: ‘low’}}, input_type=dict]

ImportError while importing test module '/home/runner/work/xxx/test_prompts.py'.
Hint: make sure your test modules/packages have valid Python names.
Traceback:
/opt/hostedtoolcache/Python/3.12.4/x64/lib/python3.12/importlib/__init__.py:90: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
test_prompts.py:10: in <module>
    from index import add_documents_to_index
../../index.py:22: in <module>
    from llama_cloud import FilterCondition
/opt/hostedtoolcache/Python/3.12.4/x64/lib/python3.12/site-packages/llama_cloud/__init__.py:3: in <module>
    from .types import (
/opt/hostedtoolcache/Python/3.12.4/x64/lib/python3.12/site-packages/llama_cloud/types/__init__.py:21: in <module>
    from .base import Base
E   ImportError: cannot import name 'Base' from 'llama_cloud.types.base' 

def initialize_index(self, namespace: str, model_name="gpt-3.5-turbo-1106"):
    service_context = ServiceContext.from_defaults(
        chunk_size=512,
        llm=OpenAI(temperature=0.7, model_name=model_name),
        callback_manager=self.callback_manager,
    )
    pinecone_index = pinecone.Index(PINECONE_INDEX_ID)
    vector_store = PineconeVectorStore(
        pinecone_index=pinecone_index,
        namespace=namespace,
    )
    storage_context = StorageContext.from_defaults(
        docstore=self.docstore,
        index_store=self.index_store,
        vector_store=vector_store,
    )
    self.index = VectorStoreIndex.from_documents(
       [], storage_context=storage_context, service_context=service_context
    )


def query_stream(self, query: str, namespace: str, model: str):
    full_query = 'Please make sure to respond ONLY with content in the .md format as the response, here is my prompt: ' + query
    self.initialize_index(namespace, model)
    streaming_response = self.index.as_query_engine(
        streaming=True, similarity_top_k=20,
    ).query(full_query)

    for text in streaming_response.response_gen:
        yield text

# this is what i want but output_cls and similarity_top_k are not accepted as args
base_query_engine = index.as_query_engine(llm=llm, filters=filters)

query_engine_presentation_content = RetryQueryEngine(
    query_engine=base_query_engine,
    output_cls=PresentationContentListV1,
    similarity_top_k=10,
)
query_engine_presentation_outline = RetryQueryEngine(
    query_engine=base_query_engine,
    output_cls=PresentationOutlineV1,
    similarity_top_k=10,
)

@app.post("/document/query")
def query_stream(
    query: str = Body(...),
    uuid_filename: str = Body(...),
    email: str = Body(...),
) -> StreamingResponse:
    subscription = get_user_subscription(email)
    model = MODEL_BASIC if subscription == "FREE" else MODEL_PREMIUM
    with token_counter(model, query_stream.__name__):
        filename_without_ext = uuid_filename.split(".")[0]

        # Create index
        index = initialize_index(model)

        document_is_indexed = does_document_exist_in_index(filename_without_ext)

        if document_is_indexed is False:
            logging.info("Re-adding to index...")
            reindex_document(filename_without_ext)

        if is_summary_request(query):
            query = modify_query_for_summary(query, filename_without_ext, model)

        chat_engine = initialize_chat_engine(index, filename_without_ext)
        streaming_response = chat_engine.stream_chat(query) # takes 10 seconds!!

        def generate() -> Generator[str, any, None]:
            yield from streaming_response.response_gen

        return StreamingResponse(generate(), media_type="text/plain")

document_store = MongoDocumentStore.from_uri(uri=MONGO_DB_URL)
index_store = MongoIndexStore.from_uri(uri=MONGO_DB_URL)

vector_store = PGVectorStore.from_params(
    async_connection_string=f"postgresql+asyncpg://{user}:{password}@{host}:{port}/{database}",
    connection_string=f"postgresql+psycopg2://{user}:{password}@{host}:{port}/{database}?sslmode=require",
    table_name=PG_VECTOR_DATABASE_DOC_TABLE_NAME,
    embed_dim=1536,
    hybrid_search=True,
    use_jsonb=True,
)

storage_context = StorageContext.from_defaults(
    docstore=document_store,
    index_store=index_store,
    vector_store=vector_store,
)

vector_store = PGVectorStore.from_params(
    async_connection_string=f"postgresql+asyncpg://{user}:{password}@{host}:{port}/{database}",
    connection_string=f"postgresql+psycopg2://{user}:{password}@{host}:{port}/{database}?sslmode=require",
    table_name=PG_VECTOR_DATABASE_DOC_TABLE_NAME,
    embed_dim=1536,
    hybrid_search=True,
    use_jsonb=True,
)

storage_context = StorageContext.from_defaults(
    vector_store=vector_store,
)

KeywordExtractor(llm, keywords=5, num_workers=24),

web-1          | [2024-02-01 10:55:21 +0000] [8] [ERROR] Exception in worker process
web-1          | Traceback (most recent call last):
web-1          |   File "/usr/local/lib/python3.11/site-packages/llama_index/storage/kvstore/mongodb_kvstore.py", line 69, in from_uri
web-1          |     from motor.motor_asyncio import AsyncIOMotorClient
web-1          | ModuleNotFoundError: No module named 'motor'
web-1          | 
web-1          | During handling of the above exception, another exception occurred:

filename_without_ext = "bla":
index = initialize_index(model)
filters = MetadataFilters(filters=[ExactMatchFilter(key="doc_id", value=filename_without_ext)])
document_is_not_indexed = len(
    index.as_retriever(filters=filters, similarity_top_k=1).retrieve("some text"),
) == 0