The Generator Update

Features

• Modular, generator-based foundation (rewrote entire codebase)
• Significantly easier to build Open Interpreter into your applications via interpreter.chat(message) (see JARVIS for example implementation)
• Run interpreter --config to configure interpreter to run with any settings by default (set your default language model, system message, etc)
• Run interpreter --conversations to resume conversations
• Budget manager (thank you LiteLLM!) via interpreter --max_budget 0.1 (sets max budget per session in USD)
• Change the system message, temperature, max_tokens, etc. from the command line
• Central /conversations folder for persistent memory
• New hosted language models (thank you LiteLLM!) like Claude, Google PaLM, Cohere, and more.

What's Changed

• Fix typo 'recieved'> 'received' by @merlinfrombelgium in #361
• Pull request template created by @TanmayDoesAI in #365
• docs: move pr template to .github folder by @jordanbtucker in #373
• chore: enhance .gitignore by @jordanbtucker in #374
• chore: add vscode debug support by @jordanbtucker in #375
• discard the / as command as it will block the Mac/Linux to load the file by @moming2k in #378
• Update interpreter.py for a typo error by @YUFEIFUT in #397
• Translated Open Interpreter README into Hindi by @zeelsheladiya in #417
• Add models to pull request template by @mak448a in #423
• Retry connecting to openai after hitting rate limit to fix #442 by @mathiasrw in #452
• Handle %load_message failure in interpreter.py by @richawo in #431
• add budget manager for api calls by @krrishdholakia in #316
• The Generator Update by @KillianLucas in #482

New Contributors

• @YUFEIFUT made their first contribution in #397
• @zeelsheladiya made their first contribution in #417
• @mak448a made their first contribution in #423
• @mathiasrw made their first contribution in #452
• @richawo made their first contribution in #431
• @krrishdholakia made their first contribution in #316

Full Changelog: v0.1.4...v0.1.5

v0.1.4

What's Changed

• Add support for R language by @freestatman in #249

• Feature: Implement and Document New Interactive Mode Commands by @moming2k in #302

• Remove previous message and its responses from chat history with Undo-command. by @oliverpalonkorp in #273

• Enable resume download from HF by @jerzydziewierz in #345

• fix: Chinese README improvements by @okisdev in #253

• ui: Optimize welcome message by @codeacme17 in #257

• feat: Add hints to Azure model by @codeacme17 in #237

• docs: Upgrade issue templates by @jordanbtucker in #262

• docs: Separate system versions into own fields by @jordanbtucker in #264

• Updated Japanese README Translation by @gijigae in #282

• Docs: use x64 in WINDOWS.md and GPU.md by @jordanbtucker in #287

• Fix using litellm.api_base, litellm.api_key, litellm.api_version by @ishaan-jaff in #284

• Fix typo. by @Michael-Lfx in #292

• fix(ui): Fix the display problem of welcome message by @codeacme17 in #270

• Better handling of split LM download by @jjolly in #278

• Docs: Add security policy by @jordanbtucker in #266

• Check disk space before downloading models by @michaelzdrav in #323

• Update GPU.md by @metantonio in #335

• remove duplicate import of inquirer library in get_hf_llm.py by @lalebot in #327

• fix: merge os.environ with llama install env_vars by @jordanbtucker in #338

• docs: move CONTRIBUTING to common path by @jordanbtucker in #350

• Fix minor typo by @osanseviero in #248

New Contributors

• @freestatman made their first contribution in #249
• @osanseviero made their first contribution in #248
• @okisdev made their first contribution in #253
• @codeacme17 made their first contribution in #257
• @gijigae made their first contribution in #282
• @Michael-Lfx made their first contribution in #292
• @jjolly made their first contribution in #278
• @michaelzdrav made their first contribution in #323
• @metantonio made their first contribution in #335
• @lalebot made their first contribution in #327
• @jerzydziewierz made their first contribution in #345

Full Changelog: v0.1.3...v0.1.4

v0.1.3

What's Changed

• Quick fix for --model tiiuae/falcon-180B (redirect to GGUF version).
• Quick fix for #247

Update pushed to pip with just the fixes above. After that, I merged this commit, which will be in the next pip version:

• Add support for R language, update instructions for package installation by @freestatman in #249

New Contributors

• @freestatman made their first contribution in #249

Full Changelog: v0.1.2...v0.1.3

v0.1.2

What's Changed

• docs: explain GPU support by @jordanbtucker in #102
• feat: add AZURE_API_KEY that falls back to OPENAI_API_KEY by @jordanbtucker in #135
• docs: explain Windows Code-Llama build requirements by @jordanbtucker in #138
• Created contribution guidelines by @TanmayDoesAI in #101
• docs: create issue templates by @jordanbtucker in #176
• moved all markdown files to a folder, updated the readme for the same… by @TanmayDoesAI in #182
• Fix download URL for CodeLlama 7B high quality model by @merlinfrombelgium in #181
• docs: add interpreter version to template by @jordanbtucker in #190
• docs: fix example version number for interpreter by @jordanbtucker in #191
• docs: add enhancement label to feature requests by @jordanbtucker in #192
• docs: prevent blank issues by @jordanbtucker in #195
• docs: provide issue template link by @jordanbtucker in #196
• Update README.md by @macterra in #197
• Create MACOS Documentation by @ihgalis in #177
• Add option to override Azure API type by @Taik in #189
• Feature: add cli environment variable by @moming2k in #157
• Update MACOS.md by @ihgalis in #215
• Falcon // Any 🤗 model via --model meta/llama by @KillianLucas in #213
• Update contributing.md with instructions on how to get local fork running by @oliverpalonkorp in #235
• remove redundant checks for apple silicon by @shubhe25p in #230
• Fix GPT 3.5 from failing to run commands by @Maclean-D in #96

New Contributors

• @jordanbtucker made their first contribution in #102
• @merlinfrombelgium made their first contribution in #181
• @macterra made their first contribution in #197
• @ihgalis made their first contribution in #177
• @Taik made their first contribution in #189
• @moming2k made their first contribution in #157
• @oliverpalonkorp made their first contribution in #235
• @shubhe25p made their first contribution in #230
• @Maclean-D made their first contribution in #96

Full Changelog: v0.1.1...v0.1.2

v0.1.1

What's Changed

• Added Azure support by @ifsheldon in #62
• CodeLlama improvements by @KillianLucas in #87
• Rate limit error fix

New Contributors

• @ifsheldon made their first contribution in #62

Full Changelog: v0.1.0...v0.1.1

v0.1.0

Open Interpreter v0.1.0

Open Interpreter lets LLMs run code locally. You can chat with Open Interpreter through a ChatGPT-like interface in your terminal by running $ interpreter after installing.

• CodeLlama supported with --local, more models coming soon
• Interpreters loaded for Python, Javascript, Shell, and Javascript
• Streaming chat in your terminal (thanks to Textualize/Rich!)

New Contributors

• @TanmayDoesAI made their first contribution in #25

Full Changelog: v0.0.297...v0.1.0

v0.0.297

What's Changed

• Windows CURL error fix by @KillianLucas in #23
• Fixed error where long conversations would hang forever (#5) by updating TokenTrim

New Contributors

• @eltociear made their first contribution in #28

Full Changelog: v0.0.296...v0.0.297

v0.0.296

Added Code Llama support.

Full Changelog: v0.0.295...v0.0.296

v0.0.295

What's Changed

• Better CLI messages
• (Experimental) Llama-2 support

v0.0.294

What's Changed

• Improved Rich active line code rendering
• Improved Open Procedures recall by @KillianLucas in #11

Full Changelog: v0.0.293...v0.0.294