summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--.github/ISSUE_TEMPLATE/model_request.md1
-rw-r--r--README.md33
2 files changed, 15 insertions, 19 deletions
diff --git a/.github/ISSUE_TEMPLATE/model_request.md b/.github/ISSUE_TEMPLATE/model_request.md
index 549b45c..36979aa 100644
--- a/.github/ISSUE_TEMPLATE/model_request.md
+++ b/.github/ISSUE_TEMPLATE/model_request.md
@@ -11,7 +11,6 @@ assignees: ''
- [ ] Must have a REST/HTTP API.
- [ ] Must be publicly accessible. It cannot require application review or have regional restrictions. A beta version is acceptable.
-- [ ] Must not open-source. Open source models can be used through LocalAI and do not need to be supported separately.
- [ ] Must not act as an agent or proxy for other platforms.
> Tip: If the API of the new model is compatible with OpenAI's API, it can be used through localai client.
diff --git a/README.md b/README.md
index 9196922..9048e91 100644
--- a/README.md
+++ b/README.md
@@ -41,31 +41,28 @@ pkg install aichat
Download it from [GitHub Releases](https://github.com/sigoden/aichat/releases), unzip and add aichat to your $PATH.
-## Support LLMs
-
-- OpenAI: gpt-3.5/gpt-4/gpt-4-vision
-- Gemini: gemini-pro/gemini-pro-vision
-- Claude: claude-instant-1.2/claude-2.0/claude-2.1
-- Mistral: mistral-small/mistral-medium/mistral-large
-- LocalAI: opensource LLMs and other openai-compatible LLMs
-- Ollama: opensource LLMs
-- Azure-OpenAI: user deployed gpt-3.5/gpt-4
-- VertexAI: gemini-pro/gemini-pro-vision/gemini-ultra/gemini-ultra-vision
-- Ernie: ernie-bot-turbo/ernie-bot/ernie-bot-8k/ernie-bot-4
-- Qianwen: qwen-turbo/qwen-plus/qwen-max/qwen-max-longcontext/qwen-vl-plus
-
## Features
-
-- Have two modes: [REPL](#chat-repl) and [Command](#command).
+- Support most of the LLM platforms
+ - OpenAI (paid, vision)
+ - Gemini (free, vision)
+ - Claude (paid)
+ - Mistral (paid)
+ - LocalAI (free, local, vision)
+ - Ollama (free, local)
+ - Azure-OpenAI (paid)
+ - VertexAI (paid, vision)
+ - Ernie (paid)
+ - Qianwen (paid, vision)
+- Support [REPL Mode](#chat-repl) and [Command Mode][#command]
- Support [Roles](#roles)
- Support context-aware conversation (session)
- Support multimodal models (vision)
- Execute commands using natural language
- Syntax highlighting for markdown and 200+ languages in code blocks
-- Stream output
-- Use proxy
-- With Dark/light theme
- Save messages/sessions
+- Stream/Non-stream output
+- With proxy
+- With Dark/light theme
## Config