Find answers from the community

Home
Members
mahdicodex999
m
mahdicodex999
Offline, last seen 3 weeks ago
Joined September 25, 2024
Hello LLama PPL , i am facing an annoying error:
Plain Text
ERROR:root:Error processing query: 1 validation error for TextNode
text
  Input should be a valid string [type=string_type, input_value=None, input_type=NoneType]
    For further information visit https://errors.pydantic.dev/2.10/v/string_type

i could not know how even to debug it right: i am using this :

Plain Text
def query_vector_store(self, query: str, top_k: int = 15):
        retriever = VectorStoreIndex.from_vector_store(self.vector_store).as_query_engine(llm=self.get_llm, similarity_top_k=top_k)
        response = retriever.query(query)
        return response

to query a vector store that is in Supabase collection is already exist, i am using this method through fastapi endpoint
5 comments
m
L
is llamaindex cloud have issue? i am getting 403 in the moment i hit GET STARTED button?
2 comments
m
L
hello devs, a bit lost with how to use Supabase VectorStore, i need to process the document once in the Upload, and then use the vector store to answer the questions. most of the examples didn't explain how can be done.
before i was creating table embeddings, and save the embedded document inside it and use sql similarity search inside Supabase.
5 comments
m
L
I am a bit confused here, i have a client who wants to chat or ask his data, this data will be scientific papers, so before llamaindex i was using long road using Openai, embeddings, save to Supabase, then query, so here i am a bit confused how to start, i need a bit advanced example if there is any please.
3 comments
m
W
J
hellos devs, i want to use the OpenWeatherMapToolSpec tool in llama-index-integrations how i can import it to use it?
2 comments
m
W
from llama_index.core.readers import SimpleDirectoryReader
it's working for me
5 comments
d
m
devs, i need to feed a system prompt to my ReAct agent, do i use it like in the.
ReAct Agent - A Simple Intro with Calculator Tools
agent.update_prompts({"agent_worker:system_prompt": react_system_prompt}) ?
2 comments
L
W
i am getting error: TypeError: FunctionTool.from_defaults() missing 1 required positional argument: 'fn'
my methods are Async functions so they need to be await

pick_func = FunctionTool.from_defaults(async_fn=flight_service.create_pickup_flight_alert)
any idea why the error is up?
7 comments
m
L
hello devs, i get lost a bit looking to use LLava model , i searched the docs and the import i found in the example it doesn't work or maybe you changed the name of the Classes, i need to use LLava to read the input images
4 comments
m
L
do i need always to write doc string for the function need to be called by LLM?
2 comments
m
L
Hello devs, i need to know if i can pass a function that is callback function for an event, inside FunctionTool.from_defaults(fn=callback_function)

def callback_function(request:Request): resp = request.json() print(resp)

so i need to trigger the agent when i receive the event... is it possible???
7 comments
m
A
@Logan M do you think it's time to bump Pydantic up and start rid off the Deprecations messages from pydantic?
example:The schema method is deprecated; use model_json_schema instead. Deprecated in Pydantic V2.0 to be removed in V3.0.
7 comments
m
L
guys i need some guide here:
i didn't understand this "The output is a valid Pydantic object that we can then use to call functions/APIs" in:
https://docs.llamaindex.ai/en/stable/examples/output_parsing/openai_pydantic_program/

i already returning the valid pydantic model from OpenAIPydanticProgram.from_defaults but i get lost where to use it, i wanna feed the generated dict to another agent so it can call a functions.
3 comments
m
L
i am getting this error whiel using UnstracturedReader()
Error: Resource averaged_perceptron_tagger not found. Please use the NLTK Downloader to obtain the resource:
i installed nltk package but still have same error
2 comments
W
m
devs i need some suggestions in my use case here:
i saving docs that have users info in Supabase bucket, i need to load it to be used by llm agent to extract the needed data , like in the example here : https://docs.llamaindex.ai/en/stable/examples/usecases/email_data_extraction/
so i need the best practice, do i need to just create temp dir and download it? or convert the needed data to Vectors and save it then retrieve it by llm.
i am a bit Lost tbh. 😟
5 comments
m
L
m
mahdicodex999
·

Branch

guys what is the roles for git branching names? example: mad/fix-bug
8 comments
m
L
ok i am having issue using openai assistant using llamaindex: i got this error:
ImportError: cannot import name 'MessageContentText' from 'openai.types.beta.threads' (/llm-test/pythonProject/.venv/lib/python3.12/site-packages/openai/types/beta/threads/__init__.py). Did you mean: 'MessageContentDelta'?
I think we need to open issue and change or update the import then open PR
5 comments
m
L