issues Search Results · repo:run-llama/llama_index language:Python
Filter by
5k results
(77 ms)5k results
inrun-llama/llama_index (press backspace or delete to remove)Question Validation
- [x] I have searched both the documentation and discord for an answer.
Question
I have deployed my own local model API , how to use it in llamaindex.
1. Is there any convenient ...
question
oldunclez
- 1
- Opened 1 hour ago
- #18115
Bug Description
While using AzureOpenAIMultiModal with VectorStoreIndex as index.as_chat_engine(llm=mm_llm) or
index.as_query_engine(llm=mm_llm) it raises AssertionError from /llama_index/core/indices/multi_modal/base.py ...
bug
triage
amanchaudhary-95
- 1
- Opened 14 hours ago
- #18111
Bug Description
I use llamaindex workflow to build Agent. I set llm objects, vector store objects, retrieved nodes in context. We
initialize the workflow globally and run the with different context for ...
bug
triage
dhanaabhirajk
- 5
- Opened 22 hours ago
- #18107
Bug Description
when i using QdrantVectorStore IngestionPipeline I got this error
NoneType object has no attribute collection_exists
Code Snippet
vector_store = QdrantVectorStore(client=qdrant_service.client, ...
bug
triage
Sanbornzhang
- 3
- Opened yesterday
- #18105
Question Validation
- [x] I have searched both the documentation and discord for an answer.
Question
Hi, To use the Custom Model, I am using the stream_complete function written as follows.
https://docs.llamaindex.ai/en/stable/api_reference/llms/custom_llm/ ...
question
jiihye
- 3
- Opened yesterday
- #18104
Bug Description
loading data using ElasticsearchReader will result in redundancy.
Version
0.12.5
Steps to Reproduce
Loading data using ElasticsearchReader will result in redundancy, because the ElasticsearchReader ...
bug
triage
minmie
- 1
- Opened yesterday
- #18102
Feature Description
Because llama-index follows the import class format, same as the library name, maybe we can change the
llama-index-integrations/llms/llama-index-llms-huggingface-api to
llama-index-integrations/llms/llama-index-llms-huggingface-inference-api. ...
enhancement
triage
julurisaichandu
- Opened yesterday
- #18101
Question Validation
- [x] I have searched both the documentation and discord for an answer.
Question
question
When using Ollama as LLMs and use function calling, the astriam_chat function will not ...
question
H4lo
- 1
- Opened yesterday
- #18099
Bug Description
the code in bold will fix the issue
_client: httpx.AsyncClient
async with httpx.AsyncClient(
headers=_headers, base_url=self._base_url, params=params, **follow_redirects=True** ...
bug
triage
maddogwithrabies
- 2
- Opened yesterday
- #18098
Bug Description
Description
There s an inconsistency in how the stream_complete method returns data between different LLM provider classes.
Specifically, there s a difference in how streaming chunks ...
bug
triage
aman-gupta-doc
- 2
- Opened yesterday
- #18096
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 IssuesProTip!
Press the /
key to activate the search input again and adjust your query.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 IssuesProTip!
Restrict your search to the title by using the in:title qualifier.