mirror of
https://github.com/run-llama/create-llama.git
synced 2026-07-15 05:08:15 -04:00
Pinecone Module Not Found in Fresh Create-Llama Setup for DuckDuckGo Search RAG #63
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @klei30 on GitHub (Sep 23, 2024).
Originally assigned to: @thucpn on GitHub.
Hi,
I'm encountering an issue with a fresh create-llama project using the Agentic RAG (DuckDuckGo Search) template. After setting it up and performing the first query, I receive an error indicating that the Pinecone module cannot be resolved.
Steps to Reproduce:
Run npx create-llama@latest.
Choose the following options:
Template: Agentic RAG (e.g., chat with docs)
Framework: NextJS
OpenAI API key: Skip
Data source: Example PDF
Add another data source: No
Use LlamaParse for RAG: No
LlamaCloud API key: Skip
Vector database: Pinecone
Tools: DuckDuckGo search, Wikipedia, Weather, Code Interpreter, etc.
Run the project and execute a query.
Error is thrown.
@robotson commented on GitHub (Sep 23, 2024):
can you try importing like
I've noticed the create-llama installer currently seem to be a little out of date with regard to where some packages are actually exported from
@klei30 commented on GitHub (Sep 23, 2024):
after i do this i also get a llamaparsereader library import problem and i do the same, but then i have an error saying :llamaindexWEBPACK_IMPORTED_MODULE_0.PineconeVectorStore is not a constructor
what "create llamaindex with ts" is stable version of both rag agent with duckduck search
i need to use both of them
@marcusschiesser commented on GitHub (Sep 24, 2024):
Sorry for the trouble. The imports and the package.jsons are now updated in create-llama 0.2.9. Please try again.
@klei30 commented on GitHub (Sep 24, 2024):
hi, yes thank you for that.
i have the same error with LLamaindexparser, i change the import into import { LlamaParseReader } from "llamaindex"; but when i do and ask chat i dont see any resources in the UI . Is there any workaround for that ?
Thanks again
@thucpn commented on GitHub (Sep 25, 2024):
Thank you, @klei30 . In my PR #322, I changed the import to
import { LlamaParseReader } from "llamaindex".LlamaParseReader is used for generating data sources, so it doesn't seem to be directly related to your chatting issue.
Can you try again?
@marcusschiesser commented on GitHub (Sep 25, 2024):
fixed in release 0.2.11