Find answers from the community

Z
ZIRU
Offline, last seen 3 months ago
Joined September 25, 2024
[Question - How to make new LlamaIndex after changing the LlamaIndex code? ]

Hi all,

I try to apply the below solution to solve rate limit issue.
https://github.com/run-llama/llama_index/issues/6398

My question is how to apply this change with my LlamaIndex Python module?
Do I need to build LlamaIndex code and install it to my python moudle to apply this change?

I clone the LlamaIndex code from https://github.com/run-llama/llama_index and follow this instraction. ( https://docs.llamaindex.ai/en/stable/getting_started/installation.html#installation-from-source )

But I dont' know now to apply my code change to apply and use the updated llamaindex with my code change in my application.

Would you please share how to develope Llamaindex with my code change to apply it?

thanks for your help.
5 comments
Z
L
❓ Do you guys know how to get a reference source file when I run query?

For example, I have multiple document files under ./data folder.

To query my question, to get the answer. I made this short code.

----------------------------------------
from llama_index import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader(input_dir="./data").load_data()
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)
------------------------------------------

I want to know what reference source file to use when the query engine is working.

Please share your knowledge. Thanks!!!!!! 👍
13 comments
Z
W
O
[Question about V0.10]
I need you guys support:

After I upgrade LlamaIndex to V0.10, I meet this Warning message.

" DeprecationWarning: Call to deprecated function (or staticmethod) download_loader. (download_loader() is deprecated. Please install tool using pip install directly instead.)"

How to install using pip? I am using " PandasCSVReader = download_loader("PandasCSVReader") "
3 comments
Z
L
Hi folks. I made LLM application using LlamaIndex. Next step is the deployment. What is the best way to deploy it using AWS? Could you please share your experience for me?
4 comments
a
Z
Hi all, I am looking for multiples query results based on similarity score?

For example.
Plain Text
from llama_index import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)


In this code, I want to get a multiple query response result with some score numbers.

| Score | Query result |
|-------|--------------|
| 0.9 |he worked. |
| 0.6 |he played. |
| 0.3 |he slept. |


What is the best way to achive my goal?

Thanks for your advice.

👍
3 comments
M
Z
L
Z
ZIRU
·

Llama Hub

How to read/load "HTTPS" web page using download_loader in ?

Hi all, I try to read web page using SimpleWebPageReader. it works well with normal web page.
But it doesn't work in HTTPS web page.

Can I read HTTPS webpage or not? If yes, how I can do..

Thanks

Error: SSLError: HTTPSConnectionPool
5 comments
T
Z