Giters
llm-edge
/
hal-9100
Edge full-stack LLM platform. Written in Rust
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
372
Watchers:
11
Issues:
79
Forks:
30
llm-edge/hal-9100 Issues
[Concept] : usable as lib & runnable on mobile etc.
Updated
6 months ago
Comments count
1
Anyone has a GPU?
Closed
6 months ago
OpenAI for retrieval seems not working
Updated
7 months ago
Comments count
4
Incorrect File Size on File List API Call
Updated
7 months ago
Removing Assistant Fails
Updated
7 months ago
[Concept] : make prompts customisable
Updated
7 months ago
"Failed to run code" fails run
Closed
7 months ago
Comments count
2
max_tokens_to_sample is negative
Closed
7 months ago
Comments count
2
When can we expect the release?
Closed
7 months ago
Comments count
1
[feat] create_and_run
Updated
8 months ago
Comments count
1
Missing field `id`
Closed
8 months ago
Comments count
2
get_step_handler() needs 3 parameters
Updated
8 months ago
Comments count
1
`Create message -> Run -> get messages` pipeline is riddled with issues.
Closed
8 months ago
Comments count
5
[function calling/action]: implement retry or redundancy
Updated
8 months ago
Comments count
1
[feat] action tool authentication
Closed
8 months ago
Comments count
3
Failing to create assistant with action tool
Closed
8 months ago
Comments count
10
Run steps returning AttributeError _set_private_attributes
Closed
8 months ago
Comments count
3
[code interpreter] does not work in kubernetes
Updated
8 months ago
[Concept] : using outlines / guidance proxy to leverage python prompt engineering ecosystem
Closed
8 months ago
tool_calls include calls from other assistants/threads
Closed
8 months ago
Comments count
4
use local llm for unit test instead of perplexity
Closed
8 months ago
Comments count
1
openai_client.files.retrieve() cannot find file.
Closed
8 months ago
Comments count
1
Model should not be needed to update assistant.
Closed
8 months ago
Comments count
2
implement steps
Closed
8 months ago
Comments count
1
"action" tool (function calling on the server)
Closed
8 months ago
Comments count
4
make ci run on pull requests and other branches
Closed
8 months ago
Comments count
2
openai.beta.assistants.list() not working
Closed
8 months ago
Comments count
1
get rid of async-openai
Closed
8 months ago
Comments count
1
fix: file name
Updated
8 months ago
Should pass Assistant's file ids to run
Updated
8 months ago
Use an env var to define the LLM to use in unit tests
Closed
8 months ago
Comments count
1
[optimization] caching requests, etc.
Updated
9 months ago
Comments count
1
cannot pass metadata to threads.
Closed
9 months ago
Comments count
1
openai.beta.assistants.create() requires more parameters than what is necessary.
Updated
9 months ago
openai_client.files.create() not being handled the same way as OpenAI
Updated
9 months ago
run cargo fix on all packages
Updated
9 months ago
unit test thoroughly multi tools assistants
Updated
9 months ago
Update assumes "set to None"
Closed
9 months ago
Comments count
1
Assistant metadata not stored
Closed
9 months ago
Comments count
2
/chat/completions
Updated
9 months ago
Comments count
1
function calling endpoint
Updated
9 months ago
How to use Mistral API end point?
Closed
9 months ago
Comments count
2
tutorial/blog post/example/demo: Bitcoin investment advisor (this is an investment advice)
Updated
9 months ago
code interpreter: pack an headless browser / browser mode or tool
Updated
9 months ago
Comments count
2
implement `last_error`, `failed_at` in run
Closed
9 months ago
Comments count
1
Example hello-world-mistral-curl Run status: failed with no reson for failure
Closed
9 months ago
Comments count
2
implement render.com one click deployment
Updated
9 months ago
list message pagination
Updated
9 months ago
Request update to: "How it Works – Visual Guide"
Closed
9 months ago
Comments count
3
Example: hello-world-anthropic-knowledge-retrieval gets hanged when uploading a PDF
Closed
9 months ago
Comments count
1
Previous
Next