Skip to content

issues Search Results · repo:run-llama/llama_index language:Python

Filter by

6k results
 (109 ms)

6k results

inrun-llama/llama_index (press backspace or delete to remove)

Bug Description Issue: Order of embeddings returned from aget_text_embedding_batch() is non-deterministic due to cache misses, causing places that depend on the order to assign wrong embeddings Expectation: ...
bug
triage
  • shedokan
  • 2
  • Opened 
    12 hours ago
  • #19537

Bug Description Expected: When using embeddings_cache non cached embeddings are fetched in batches Actual: When using embeddings_cache all non-cached embeddings are fetched one by one We can see this ...
bug
triage
  • shedokan
  • 3
  • Opened 
    14 hours ago
  • #19535

Bug Description There s a bug in the source file suggest in this guide: https://docs.llamaindex.ai/en/stable/examples/vector_stores/OpensearchDemo . The bug lies in the script file llama_index/core/download/dataset.py ...
bug
triage
  • MarcoOttina
  • Opened 
    20 hours ago
  • #19533

Question Validation - [x] I have searched both the documentation and discord for an answer. Question Hi, Does anyone have any suggestions to fix the problem im facing? Currenty I m working with LLamaIndex ...
question
  • LukasViolet88
  • 2
  • Opened 
    yesterday
  • #19531

Feature Description There should be an option to set aws region dynamically instead of via environment variable. Reason I am trying to integrate S3Reader to my FastApi app and the users need to provide ...
enhancement
triage
  • nubufi
  • Opened 
    yesterday
  • #19530

Bug Description I m trying to migrate my RAG workflow from FAISS to S3Vectors. Using the BM25Retriever seems to fail when using the index from S3Vectors. Version 0.12.52 Steps to Reproduce vector_store ...
bug
triage
  • rileyhun
  • 4
  • Opened 
    yesterday
  • #19527

Bug Description When running the tests under llama-index-integrations/llms/llama-index-llms-nvidia, I got FAILED tests/test_base_url.py::test_base_url_valid_hosted_with_api_key[https://integrate.api.nvidia.com/v1/] ...
bug
triage
  • jiayin-nvidia
  • 1
  • Opened 
    yesterday
  • #19523

Bug Description I m getting the following error: ValidationException: An error occurred (ValidationException) when calling the PutVectors operation: Invalid record for key 70a9e29c-52f3-4123-94cc-6e528c94c989 ...
bug
triage
  • rileyhun
  • 2
  • Opened 
    yesterday
  • #19522

Question Validation - [x] I have searched both the documentation and discord for an answer. Question The llama_index import is very slow and it is using Windows.
question
  • zhaojiangbing
  • 2
  • Opened 
    2 days ago
  • #19518

Question Validation - [x] I have searched both the documentation and discord for an answer. Question [Question]: How can i use BatchEvalRunner without query_engine i have my batch query 、batch contexts、batch ...
question
  • gctian
  • 3
  • Opened 
    2 days ago
  • #19517
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub