0.5.0

版本发布时间: 2024-10-15 09:47:55

letta-ai/letta最新发布版本:0.5.2(2024-11-07 15:00:40)

This release introduces major changes to how model providers are configured with Letta, as well as many bugfixes.

🧰 Dynamic model listing and multiple providers (#1814)

Model providers (e.g. OpenAI, Ollama, vLLM, etc.) are now enabled using environment variables, where multiple providers can be enabled at a time. When a provider is enabled, all supported LLM and embedding models will be listed as options to be selected in the CLI and ADE in a dropdown.

For example for OpenAI, you can simply get started with:

> export OPENAI_API_KEY=...
> letta run 
   ? Select LLM model: (Use arrow keys)
   » letta-free [type=openai] [ip=https://inference.memgpt.ai]
      gpt-4o-mini-2024-07-18 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o-mini [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o-2024-08-06 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o-2024-05-13 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-turbo-preview [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-turbo-2024-04-09 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-turbo [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-1106-preview [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-0613 [type=openai] [ip=https://api.openai.com/v1]
     ...

Similarly, if you are using the ADE with letta server, you can select the model to use from the model dropdown.

# include models from OpenAI 
> export OPENAI_API_KEY=...

# include models from Anthropic 
> export ANTHROPIC_API_KEY=... 

# include models served by Ollama 
> export OLLAMA_BASE_URL=...

> letta server

We are deprecating the letta configure and letta quickstart commands, and the the use of ~/.letta/config for specifying the default LLMConfig and EmbeddingConfig, as it prevents a single letta server from being able to run agents with different model configurations concurrently, or to change the model configuration of an agent without re-starting the server. This workflow also required users to specify the model name, provider, and context window size manually via letta configure.

🧠 Integration testing for model providers

We added integration tests (including testing of MemGPT memory management tool-use) for the following model providers, and fixed many bugs in the process:

OpenAI #1827
Anthropic #1837
Azure OpenAI #1871 #1842
Groq #1845
Google AI (Gemini) #1850

📊 Database migrations

We now support automated database migrations via alembic, implemented in https://github.com/cpacker/MemGPT/pull/1867. You can expect future release to support automated migrations even if there are schema changes.

What's Changed

feat: add back support for using AssistantMessage subtype of LettaMessage by @cpacker in https://github.com/cpacker/MemGPT/pull/1812
feat: Add Groq as provider option by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1815
chore: allow app.letta.com access to local if user grants permission by @4shub in https://github.com/cpacker/MemGPT/pull/1830
feat: Set up code scaffolding for complex e2e tests and write tests for OpenAI GPT4 endpoint by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1827
feat: require LLMConfig and EmbeddingConfig to be specified for agent creation + allow multiple simultaneous provider configs for server by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1814
test: Add complex e2e tests for anthropic opus-3 model by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1837
refactor: remove get_current_user and replace with direct header read by @cpacker in https://github.com/cpacker/MemGPT/pull/1834
Docker compose vllm by @hitpoint6 in https://github.com/cpacker/MemGPT/pull/1821
fix: Fix Azure provider and add complex e2e testing by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1842
fix: patch user_id in header by @cpacker in https://github.com/cpacker/MemGPT/pull/1843
feat: add agent types by @vivek3141 in https://github.com/cpacker/MemGPT/pull/1831
feat: list out embedding models for Google AI provider by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1839
test: add complex testing for Groq Llama 3.1 70b by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1845
feat: persist tools to db when saving agent by @vivek3141 in https://github.com/cpacker/MemGPT/pull/1847
feat: list available embedding/LLM models for ollama by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1840
feat: Add listing llm models and embedding models for Azure endpoint by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1846
fix: remove testing print by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1849
fix: calling link_tools doesnt update agent.tools by @vivek3141 in https://github.com/cpacker/MemGPT/pull/1848
fix: refactor Google AI Provider / helper functions and add endpoint test by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1850
fix: factor out repeat POST request logic by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1851
fix: CLI patches - patch runtime error on main loop + duplicate internal monologue by @cpacker in https://github.com/cpacker/MemGPT/pull/1852
test: add complex gemini tests by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1853
chore: deprecate letta configure and remove config defaults by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1841
chore: add CLI CI test by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1858
fix: insert_many checks exists_ok by @vivek3141 in https://github.com/cpacker/MemGPT/pull/1861
fix: delete agent-source mapping on detachment and add test by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1862
feat: cleanup display of free endpoint by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1860
fix: add missing hardcodings for popular OpenAI models by @cpacker in https://github.com/cpacker/MemGPT/pull/1863
chore: fix branch by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1865
chore: add e2e tests for Groq to CI by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1868
test: Fix Azure tests and write CI tests by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1871
chore: support alembic by @4shub in https://github.com/cpacker/MemGPT/pull/1867
fix: fix typo by @kl2806 in https://github.com/cpacker/MemGPT/pull/1870
feat: add VLLMProvider by @sarahwooders in https://github.com/cpacker/MemGPT/pull/1866
fix: Fix config bug in alembic by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1873
fix: patch errors with OllamaProvider by @cpacker in https://github.com/cpacker/MemGPT/pull/1875
refactor: simplify Agent.step inputs to Message or List[Message] only by @cpacker in https://github.com/cpacker/MemGPT/pull/1879
feat: Enable adding files by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1864
feat: refactor the POST agent/messages API to take multiple messages by @cpacker in https://github.com/cpacker/MemGPT/pull/1882
feat: Add MistralProvider by @mattzh72 in https://github.com/cpacker/MemGPT/pull/1883

New Contributors

@hitpoint6 made their first contribution in https://github.com/cpacker/MemGPT/pull/1821
@vivek3141 made their first contribution in https://github.com/cpacker/MemGPT/pull/1831
@kl2806 made their first contribution in https://github.com/cpacker/MemGPT/pull/1870

Full Changelog: https://github.com/cpacker/MemGPT/compare/0.4.1...0.5.0

相关地址：原始地址下载(tar) 下载(zip)

查看：2024-10-15发行的版本