To use Letta with Together.AI, set the environment variable TOGETHER_API_KEY=...

You can use Letta with Together.AI if you have an account and API key. Once you have set your TOGETHER_API_KEY in your environment variables, you can select what model and configure the context window size.

Enabling Together.AI as a provider

To enable the Together.AI provider, you must set the TOGETHER_API_KEY environment variable. When this is set, Letta will use available LLM models running on Together.AI.

Using the docker run server with Together.AI

To enable Together.AI models, simply set your TOGETHER_API_KEY as an environment variable:

$# replace `~/.letta/.persist/pgdata` with wherever you want to store your agent data
>docker run \
> -v ~/.letta/.persist/pgdata:/var/lib/postgresql/data \
> -p 8283:8283 \
> -e TOGETHER_API_KEY="your_together_api_key" \
> letta/letta:latest

Using letta run and letta server with Together.AI

To chat with an agent, run:

$export TOGETHER_API_KEY="..."
>letta run

This will prompt you to select a model:

$? Select LLM model: (Use arrow keys)
> » letta-free [type=openai] [ip=https://inference.memgpt.ai]
> codellama/CodeLlama-34b-Instruct-hf [type=together] [ip=https://api.together.ai/v1]
> upstage/SOLAR-10.7B-Instruct-v1.0 [type=together] [ip=https://api.together.ai/v1]
> mistralai/Mixtral-8x7B-v0.1 [type=together] [ip=https://api.together.ai/v1]
> meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo [type=together] [ip=https://api.together.ai/v1]
> togethercomputer/Llama-3-8b-chat-hf-int4 [type=together] [ip=https://api.together.ai/v1]
> google/gemma-2b-it [type=together] [ip=https://api.together.ai/v1]
> Gryphe/MythoMax-L2-13b [type=together] [ip=https://api.together.ai/v1]
> mistralai/Mistral-7B-Instruct-v0.1 [type=together] [ip=https://api.together.ai/v1]
> mistralai/Mistral-7B-Instruct-v0.2 [type=together] [ip=https://api.together.ai/v1]
> meta-llama/Meta-Llama-3-8B [type=together] [ip=https://api.together.ai/v1]
> mistralai/Mistral-7B-v0.1 [type=together] [ip=https://api.together.ai/v1]
> meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo [type=together] [ip=https://api.together.ai/v1]
> deepseek-ai/deepseek-llm-67b-chat [type=together] [ip=https://api.together.ai/v1]
> ...

To run the Letta server, run:

$export TOGETHER_API_KEY="..."
>letta server

To select the model used by the server, use the dropdown in the ADE or specify a LLMConfig object in the Python SDK.

Built with