query_engine = CitationQueryEngine.from_args(
        index=temp_index,
        similarity_top_k=3,
        citation_chunk_size=512,
        system_prompt="Doesn't matter what user asks, always reply with: `I love bananas`"
    )

1) in PDF-A it is written that Microsoft made profit in 2021, but in PDF-B it is written that Microsoft made loss in 2021

2) Based on PDF-A, Apple spends more money on design than on technology, however in PDF-B it is stated that Apple spends more money on techonlogy etc.

  File "/home/ali/AI/nexus/llm-topic-modelling/venv/lib/python3.10/site-packages/nest_asyncio.py", line 193, in _patch_loop
    raise ValueError('Can\'t patch loop of type %s' % type(loop))
ValueError: Can't patch loop of type <class 'uvloop.Loop'>

file_extractor = {".pdf": parser}
documents = SimpleDirectoryReader(
    "./docs/pdfs/all", file_extractor=file_extractor
).load_data()

You are a professional Business Analyst bla bla bla

@app.post("/query/")
def process_text(request_body: dict, db: Session = Depends(get_db)):
    query = request_body.get('query')
    vector_store = QdrantVectorStore(client=client, collection_name="data")
    index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
    query_engine = index.as_query_engine()
    response = query_engine.query(query)
    return response.response

llm.complete(prompt)

pydantic_core._pydantic_core.ValidationError: 3 validation errors for Data102Model
scope_1_emissions
  Field required [type=missing, input_value={}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.6/v/missing
scope_2_emissions_location_based
  Field required [type=missing, input_value={}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.6/v/missing
scope_3_emissions
  Field required [type=missing, input_value={}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.6/v/missing

class Data102Model(BaseModel):
    """Data model of scope 1,2 and 3 emissions"""
    scope_1_emissions: str = Field(
        description='scope 1 emissions value. If not found, return "not mentioned"')
    scope_2_emissions_location_based: str = Field(
        description='location based scope 2 emissions value. If not found, return "not mentioned"')
    scope_3_emissions: str = Field(
        description='scope 3 emissions value. If not found, return "not mentioned"')

class ClimateChangeTarget(BaseModel):
    """Data model for climate change target"""
    target_reduction_of_emission: str # I want to write what I mean by this field
    base_year: int # I want to write what I mean by this field
    timeline: str # I want to write what I mean by this field
    target_description: str # I want to write what I mean by this field


class Data101Model(BaseModel):
    """Data model for climate change targets"""
    overall_target: ClimateChangeTarget  # I want to write what I mean by this field
    scope_1: ClimateChangeTarget # I want to write what I mean by this field
    scope_2: ClimateChangeTarget # I want to write what I mean by this field
    scope_3: ClimateChangeTarget # I want to write what I mean by this field

    pipeline = IngestionPipeline(
        transformations=[
            TokenTextSplitter(chunk_size=1024, chunk_overlap=300),
            OpenAIEmbedding()
        ],
        vector_store=vector_store
    )

    pipeline.run(documents=documents)

    vector_store = QdrantVectorStore(client=qdrant_vectorstore_client,
                                     collection_name=str(uuid.uuid4()))
    
    index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
    retriever = index.as_retriever()
    nodes = retriever.retrieve(question)

        embed_model = HuggingFaceEmbedding(model_name="WhereIsAI/UAE-Large-V1")
        documents = [Document(text="...", metadata={...}), Document(text=",,,", metadata={...})]

        pipeline=[
            TokenTextSplitter(
                chunk_size=512,
                chunk_overlap=20,
                separator=" "
            ),
            embed_model
        ]

      pipeline.run(documents=documents)

{"id_": "04fd0f75-0641-4ff9-96df-da768e99922c", "embedding": null,

service_context = ServiceContext.from_defaults()
vector_store = QdrantVectorStore(client=client, collection_name="paul_graham")
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, service_context=service_context
)
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")

service_context = ServiceContext.from_defaults(llm=llm, embed_model="local:WhereIsAI/UAE-Large-V1")

embed_model = HuggingFaceEmbedding(model_name="local:WhereIsAI/UAE-Large-V1")

from fastapi import File, UploadFile
from typing import List

async def upload_files(pdf_files: List[UploadFile] = File(...)):
  for pdf_file in pdf_files:
      # what loader do I need to use? Do I need to first read the text contents myself and create a list of Documents?

query_engine = index.as_query_engine(similarity_top_k=1)
response = query_engine.query("query")

llm = Ollama(model="model")
...
query_engine = index.as_query_engine()
response = query_engine.query("query")

TimeoutError: timed out
...
httpcore.ReadTimeout: timed out
...
httpx.ReadTimeout: timed out