v0.14.0

Breaking Changes

Compress session automaticlly (#333)

When the total number of tokens in the session messages exceeds compress_threshold, aichat will automatically compress the session.

This means you can chat forever in the session.

The default compress_threshold is 2000, set this value to zero to disable automatic compression.

Rename max_tokens to max_input_tokens (#339)

To avoid misunderstandings. The max_input_tokens also be referred to as context_window.

    models:
      - name: mistral
--      max_tokens: 8192
++      max_input_tokens: 8192

New Models

• claude

  • claude:claude-3-opus-20240229
  • claude:claude-3-sonnet-20240229
  • claude:claude-2.1
  • claude:claude-2.0
  • claude:claude-instant-1.2

• mistral

  • mistral:mistral-small-latest
  • mistral:mistral-medium-latest
  • mistral:mistral-larget-latest
  • mistral:open-mistral-7b
  • mistral:open-mixtral-8x7b

• ernie

  • ernie:ernie-3.5-4k-0205
  • ernie:ernie-3.5-8k-0205
  • ernie:ernie-speed

Commmand Changes

• -c/--code generate code only (#327)

Chat-REPL Changes

• .clear messages to clear session messages (#332)

Miscellences

• shell integrations (#323)
• allow overriding execute/code role (#331)

Full Changelog: v0.13.0...v0.14.0

v0.13.0

What's Changed

• fix: copy on linux wayland by @sigoden in #288
• fix: deprecation warning of .read command by @Nicoretti in #296
• feat: supports model capabilities by @sigoden in #297
• feat: add openai.api_base config by @sigoden in #302
• feat: add extra_fields to models of localai/ollama clients by @kelvie in #298
• fix: do not attempt to deserialize zero byte chunks in ollama stream by @JosephGoulden in #303
• feat: update openai/qianwen/gemini models by @sigoden in #306
• feat: support vertexai by @sigoden in #308
• refactor: update vertexai/gemini/ernie clients by @sigoden in #309
• feat: edit current prompt on $VISUAL/$EDITOR by @sigoden in #314
• refactor: change header of messages saved to markdown by @sigoden in #317
• feat: support -e/--execute to execute shell command by @sigoden in #318
• refactor: improve prompt error handling by @sigoden in #319
• refactor: improve saving messages by @sigoden in #322

New Contributors

• @Nicoretti made their first contribution in #296
• @kelvie made their first contribution in #298
• @JosephGoulden made their first contribution in #303

Full Changelog: v0.12.0...v0.13.0

v0.12.0

What's Changed

• feat: change REPL indicators #263
• fix: pipe failed on macos #264
• fix: cannot read image with uppercase ext #270
• feat: support gemini #273
• feat: abandon PaLM2 #274
• feat: support qianwen:qwen-vl-plus #275
• feat: support ollama #276
• feat: qianwen vision models support embeded images #277
• refactor: remove path existence indicator from info #282
• feat: custom REPL prompt #283

Full Changelog: v0.11.0...v0.12.0

v0.11.0

What's Changed

• refactor: improve render #235
• feat: add a spinner to indicate waiting for response #236
• refactor: qianwen client use incremental_output #240
• fix: the last reply tokens was not highlighted #243
• refactor: ernie client system message #244
• refactor: palm client system message #245
• refactor: trim trailing spaces from the role prompt #246
• feat: support vision #249
• feat: state-aware completer #251
• feat: add ernie:ernie-bot-8k qianwen:qwen-max #252
• refactor: sort of some complete type #253
• feat: allow shift-tab to select prev in completion menu #254

Full Changelog: v0.10.0...v0.11.0

v0.10.0

New features

Use ::: for multi-line editing, deprecate .edit

〉::: This
is
a
multi-line
message
:::

Temporarily use a role to send a message.

coder〉.role shell how to unzip a file
unzip file.zip

coder〉

As shown above, you temporarily switched to the shell role in the coder role and sent a message. After sending, the current role is still coder.

Set default role/session with config.prelude

For those who want aichat to enter a session after startup, you can set it as follows:

prelude: session:mysession

For those who want aichat to use a role after startup, you can set it as follows:

prelude: role:myrole

Use a model that is not in the --list-models

If OpenAI releases a new model in the future, it can be used without upgrading Aichat.

$ aichat --model openai:gpt-4-vision-preview
〉.model openai:gpt-4-vision-preview

Changelog

• refactor: improve error message for PaLM client by @sigoden in #213
• refactor: rename Model.llm_name to name by @sigoden in #216
• refactor: use &GlobalConfig to avoid clone by @sigoden in #217
• refactor: remove Model.client_index, match client by name by @sigoden in #218
• feat: allow the use of an unlisted model by @sigoden in #219
• fix: unable to build on android using termux by @sigoden in #222
• feat: add config.prelude to allow setting default role/session by @sigoden in #224
• feat: deprecate .edit, use """ instead by @sigoden in #225
• refactor: improve repl completer by @sigoden in #226
• feat: temporarily use a role to send a message by @sigoden in #227
• refactor: output info contains auto_copy and light_theme by @sigoden in #230
• fix: unexpected additional newline in REPL by @sigoden in #231
• refactor: use ::: as multipline input indicator, deprecate """ by @sigoden in #232
• feat: add openai:gpt-4-1106-preview by @sigoden in #233

Full Changelog: v0.9.0...v0.10.0

v0.9.0

Support multiple LLMs/Platforms

• OpenAI: gpt-3.5/gpt-4
• LocalAI: opensource models
• Azure-OpenAI: user deployed gpt3.5/gpt4
• PaLM: chat-bison-001
• Ernie: eb-instant/ernie-bot/ernie-bot-4
• Qianwen: qwen-turbo/qwen-plus

Enhance session/conversation

New in command mode

      --list-sessions        List all available sessions
  -s, --session [<SESSION>]  Create or reuse a session

New in chat mode

.session                 Start a context-aware chat session
.info session            Show session info
.exit session            End the current session

Other features:

• Able to start a conversation that incorporates the last question and answer.
• Deprecate config.conversation_first, use aichat -s instead.
• Ask for saving session when exit.

Show information

In command mode

aichat --info                     # Show system info
aichat --role shell --info        # Show role info
aichat --session temp  --info     # Show session info

In chat mode

.info                    Print system info
.info role               Show role info
.info session            Show session info

Support textwrap

Configuration:

wrap: no                         # Specify the text-wrapping mode (no*, auto, <max-width>)
wrap_code: false                 # Whether wrap code block

Command:

aichat -w 120          # set max width
aichat -w auto         # use term width
aichat -w no           # no wrap

New Configuration

light_theme: false               # If set true, use light theme
wrap: no                         # Specify the text-wrapping mode (no*, auto, <max-width>)
wrap_code: false                 # Whether wrap code block
auto_copy: false                 # Automatically copy the last output to the clipboard
keybindings: emacs               # REPL keybindings, possible values: emacs (default), vi

Chat REPL changelog

• Add .copy to Copy the last output to the clipboard
• Add .read to Read the contents of a file and submit
• Add .edit for Multi-line editing (CTRL+S to finish)
• Add .info session to show system info
• Add .info role to show role info
• Rename .conversation to .session
• Rename .clear conversation to .exit session
• Rename .clear role to .exit role
• Deprecate .clear
• Deprecate .prompt
• Deprecate .hisotry .clear history

Other changes

• Support bracketed paste, You can directly paste multiple lines of text
• Suppport customize theme
• Replace AICHAT_API_KEY with OPENAI_API_KEY, Also support OPENAI_API_BASE
• Fix duplicate lines in kitty terminal
• Deprecate prompt, both --prompt and .prompt are removed

v0.8.0

What's Changed

• feat: support multiple models by @sigoden in #71
• feat: add config.connect_timeout by @sigoden in #76
• feat: add config.organization_id by @sigoden in #77
• feat: add --info by @sigoden in #79
• feat: check token usage in dry_run mode by @sigoden in #82
• feat: add --dry-run by @sigoden in #83

Full Changelog: v0.7.0...v0.8.0

v0.7.0

What's Changed

• feat: provide --prompt for adding a prompt from cli by @sigoden in #62
• feat: support more env vars by @sigoden in #63
• feat: support light theme by @sigoden in #65
• feat: add support for NO_COLOR by @sigoden in #67
• feat: support HTTPS_PROXY and ALL_PROXY by @sigoden in #68
• feat: support role args by @sigoden in #69

Full Changelog: v0.6.0...v0.7.0

v0.6.0

What's Changed

• feat: add role info to readline indicator by @sigoden in #47
• feat: support conversation by @sigoden in #48
• fix: abort by ctrlc unexpectedly prints error message by @sigoden in #49
• feat: add remain tokens indicator and max tokens guard by @sigoden in #50
• feat: support two types of role prompts by @sigoden in #52
• feat: add config.conversation_first by @sigoden in #55
• feat: type { [ ( to enter multi-line editing mode by @sigoden in #58

Full Changelog: v0.5.0...v0.6.0

v0.5.0

What's Changed

• refactor: use syntect for highlight, abandon mdcat by @sigoden in #26
• refactor: optimize ctrl+c/ctrl+d abort handling by @sigoden in #27
• refactor: support highlighting more languages by @sigoden in #28
• refactor: adjust repl by @sigoden in #30
• feat: command mode supports stream out by @sigoden in #31
• refactor: theme and code color by @sigoden in #32
• refactor: split long paragraphs for smoother stream output by @sigoden in #33
• fix: repl set save true not work if not rerun by @sigoden in #34
• refactor: replace dump with print_now! by @sigoden in #35
• fix: windows no stream output by @sigoden in #37
• feat: add role-specific config by @sigoden in #42

Full Changelog: v0.4.0...v0.5.0