Find answers from the community

Home
Members
FullEmpty
F
FullEmpty
Offline, last seen 2 months ago
Joined October 29, 2024
Plain Text
INFO:llama_index.core.indices.struct_store.sql_retriever:> Table desc str: Table 'instructors' has columns: id (INTEGER), name (VARCHAR), email (VARCHAR), organization (VARCHAR), exam_name (VARCHAR), date_created (DATETIME), and foreign keys: .
INFO:httpx:HTTP Request: POST https://integrate.api.nvidia.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-11-02 00:30:28,341 INFO sqlalchemy.engine.Engine BEGIN (implicit)
INFO:sqlalchemy.engine.Engine:BEGIN (implicit)
2024-11-02 00:30:28,341 INFO sqlalchemy.engine.Engine INSERT INTO instructors (name, email, organization, exam_name) VALUES ('John Doe', 'great@good.com', 'numver1', 'special term');
INFO:sqlalchemy.engine.Engine:INSERT INTO instructors (name, email, organization, exam_name) VALUES ('John Doe', 'great@good.com', 'numver1', 'special term');
2024-11-02 00:30:28,341 INFO sqlalchemy.engine.Engine [generated in 0.00020s] ()
INFO:sqlalchemy.engine.Engine:[generated in 0.00020s] ()
2024-11-02 00:30:28,342 INFO sqlalchemy.engine.Engine COMMIT
INFO:sqlalchemy.engine.Engine:COMMIT
INFO:httpx:HTTP Request: POST https://integrate.api.nvidia.com/v1/chat/completions "HTTP/1.1 200 OK"
PRINT OUTPUT: ** (SQL Syntax Error)

The generated SQL INSERT statement is correct, but it seems that there is an error in the execution of the query. The error message is not specific, but here are some potential issues:

* **Typo in table or column names**: Make sure that the table name "instructors" and column names "name", "email", "organization", and "exam_name" are spelled correctly and match the actual table schema.
* **Data type mismatch**: Verify that the data types of the values being inserted match the data types of the corresponding columns. For example, if the "email" column is defined as a unique identifier, inserting a string value may cause an error.
4 comments
F
L
Hi, I'm using NVIDIA module. It works fine for any model, except for nemotron models (which work smooth with native OpenAI library). Is there any idea on that?

Plain Text
from llama_index.llms.nvidia import NVIDIA

    Settings.llm = NVIDIA(model="nvidia/nemotron-4-51b-instruct", ...)


Plain Text
INFO:httpx:HTTP Request: POST https://integrate.api.nvidia.com/v1/chat/completions "HTTP/1.1 404 Not Found"

...

  File "/home/0/miniconda3/envs/gpu_rag/lib/python3.10/site-packages/openai/_base_client.py", line 1058, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: 404 page not found
8 comments
F
L
@BerndPra Hi, I ran into the exact same issue and joined here to learn. Thanks for your asking. Could you share your experience with llama_deploy? I'm not sure if it works the same way as llama_agents description.
1 comment
L