Langroid

Latest version: v0.2.2

Safety actively analyzes 638437 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 30 of 41

* Fix repeat print of LLM response in stream + async mode
* Disallow fn-calling when LLM is not an OpenAI mdl

Minor: set vecdb = None by default in Configs

Non-OpenAI model specs: Allow chat_model to be one of these forms:
litellm/ollama/mistral
local/localhost:8000

* Update to LiteLLM 0.6.2 (fixes some async issues)
* Simplify langroid settings inference for local models

None

Added LiteLLM to allow using Langroid with 100+ local/remote LLMs
(Docs coming soon)

Has known vulnerabilities

Previous Next