letta-configuration

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Letta Configuration

Letta 配置

Complete guide for configuring models on agents and providers on servers.

关于在Agent上配置模型、在服务器上配置提供商的完整指南。

When to Use This Skill

何时使用该技能

Agent-level (model configuration):

Creating agents with specific model configurations
Adjusting model settings (temperature, max tokens, context window)
Configuring provider-specific features (OpenAI reasoning, Anthropic thinking)
Changing models on existing agents

Server-level (provider configuration):

Setting up BYOK (bring your own key) providers
Configuring self-hosted deployments with environment variables
Validating provider credentials
Setting up custom OpenAI-compatible endpoints

Not covered here: Model selection advice (which model to choose) - see

agent-development

skill.

Agent层面（模型配置）：

创建带有特定模型配置的Agent
调整模型设置（temperature、max tokens、context window）
配置提供商专属功能（OpenAI推理、Anthropic思维扩展）
为已有的Agent更换模型

服务器层面（提供商配置）：

搭建BYOK（自带密钥）提供商
通过环境变量配置自托管部署
验证提供商凭证
搭建自定义OpenAI兼容端点

本文未涵盖： 模型选择建议（如何选择模型）- 请查看

agent-development

技能文档。

Part 1: Model Configuration (Agent-Level)

第一部分：模型配置（Agent层面）

Model Handles

模型句柄

Models use a

provider/model-name

format:

Provider	Handle Prefix	Example
OpenAI	`openai/`	`openai/gpt-4o` , `openai/gpt-4o-mini`
Anthropic	`anthropic/`	`anthropic/claude-sonnet-4-5-20250929`
Google AI	`google_ai/`	`google_ai/gemini-2.0-flash`
Azure OpenAI	`azure/`	`azure/gpt-4o`
AWS Bedrock	`bedrock/`	`bedrock/anthropic.claude-3-5-sonnet`
Groq	`groq/`	`groq/llama-3.3-70b-versatile`
Together	`together/`	`together/meta-llama/Llama-3-70b`
OpenRouter	`openrouter/`	`openrouter/anthropic/claude-3.5-sonnet`
Ollama (local)	`ollama/`	`ollama/llama3.2`

模型采用

provider/model-name

格式：

提供商	句柄前缀	示例
OpenAI	`openai/`	`openai/gpt-4o` , `openai/gpt-4o-mini`
Anthropic	`anthropic/`	`anthropic/claude-sonnet-4-5-20250929`
Google AI	`google_ai/`	`google_ai/gemini-2.0-flash`
Azure OpenAI	`azure/`	`azure/gpt-4o`
AWS Bedrock	`bedrock/`	`bedrock/anthropic.claude-3-5-sonnet`
Groq	`groq/`	`groq/llama-3.3-70b-versatile`
Together	`together/`	`together/meta-llama/Llama-3-70b`
OpenRouter	`openrouter/`	`openrouter/anthropic/claude-3.5-sonnet`
Ollama（本地）	`ollama/`	`ollama/llama3.2`

Basic Model Configuration

基础模型配置

python

from letta_client import Letta

client = Letta(api_key="your-api-key")

agent = client.agents.create(
    model="openai/gpt-4o",
    model_settings={
        "provider_type": "openai",  # Required - must match model provider
        "temperature": 0.7,
        "max_output_tokens": 4096,
    },
    context_window_limit=128000
)

python

from letta_client import Letta

client = Letta(api_key="your-api-key")

agent = client.agents.create(
    model="openai/gpt-4o",
    model_settings={
        "provider_type": "openai",  # Required - must match model provider
        "temperature": 0.7,
        "max_output_tokens": 4096,
    },
    context_window_limit=128000
)

Common Settings

通用设置

Setting	Type	Description
`provider_type`	string	Required. Must match model provider ( `openai` , `anthropic` , `google_ai` , etc.)
`temperature`	float	Controls randomness (0.0-2.0). Lower = more deterministic.
`max_output_tokens`	int	Maximum tokens in the response.

设置项	类型	描述
`provider_type`	string	必填项。必须与模型提供商匹配（ `openai` , `anthropic` , `google_ai` 等）
`temperature`	float	控制输出随机性（取值范围0.0-2.0）。值越低，输出越具确定性。
`max_output_tokens`	int	响应中的最大令牌数。

Changing an Agent's Model

更换Agent的模型

python

client.agents.update(
    agent_id=agent.id,
    model="anthropic/claude-sonnet-4-5-20250929",
    model_settings={"provider_type": "anthropic", "temperature": 0.5},
    context_window_limit=64000
)

Note: Agents retain memory and tools when changing models.

python

client.agents.update(
    agent_id=agent.id,
    model="anthropic/claude-sonnet-4-5-20250929",
    model_settings={"provider_type": "anthropic", "temperature": 0.5},
    context_window_limit=64000
)

注意： 更换模型时，Agent会保留其记忆与工具。

Provider-Specific Settings

提供商专属设置

For OpenAI reasoning models and Anthropic extended thinking, see

references/provider-settings.md

关于OpenAI推理模型和Anthropic扩展思维功能的配置，请查看

references/provider-settings.md

。

Part 2: Provider Configuration (Server-Level)

第二部分：提供商配置（服务器层面）

Quick Start

快速开始

bash

undefined

bash

undefined

Add provider via API

python scripts/setup_provider.py --type openai --api-key sk-...

Generate .env for Docker

python scripts/generate_env.py --providers openai,anthropic,ollama

Validate credentials

python scripts/validate_provider.py --provider-id provider-xxx

undefined

python scripts/validate_provider.py --provider-id provider-xxx

undefined

Add BYOK Provider

添加BYOK提供商

python

undefined

python

undefined

Via REST API

curl -X POST http://localhost:8283/v1/providers
-H "Content-Type: application/json"
-d '{ "name": "My OpenAI", "provider_type": "openai", "api_key": "sk-your-key-here" }'

undefined

curl -X POST http://localhost:8283/v1/providers
-H "Content-Type: application/json"
-d '{ "name": "My OpenAI", "provider_type": "openai", "api_key": "sk-your-key-here" }'

undefined

Supported Provider Types

支持的提供商类型

openai

anthropic

azure

google_ai

google_vertex

ollama

groq

deepseek

xai

together

mistral

cerebras

bedrock

vllm

sglang

hugging_face

lmstudio_openai

For detailed configuration of each provider, see:

```
references/common_providers.md
```
- OpenAI, Anthropic, Azure, Google
```
references/self_hosted_providers.md
```
- Ollama, vLLM, LM Studio
```
references/all_providers.md
```
- Complete reference
```
references/environment_variables.md
```
- Docker/self-hosted setup

openai

anthropic

azure

google_ai

google_vertex

ollama

groq

deepseek

xai

together

mistral

cerebras

bedrock

vllm

sglang

hugging_face

lmstudio_openai

如需每个提供商的详细配置说明，请查看：

```
references/common_providers.md
```
- OpenAI、Anthropic、Azure、Google
```
references/self_hosted_providers.md
```
- Ollama、vLLM、LM Studio
```
references/all_providers.md
```
- 完整参考手册
```
references/environment_variables.md
```
- Docker/自托管部署配置

Anti-Hallucination Checklist

防幻觉检查清单

Before configuring:

Model handle uses correct
```
provider/model-name
```
format
```
model_settings
```
includes required
```
provider_type
```
field
```
context_window_limit
```
is set at agent level, not in
```
model_settings
```
Provider-specific settings use correct nested structure
For self-hosted: embedding model is specified
Temperature is within valid range (0.0-2.0)

配置前请确认：

模型句柄使用正确的
```
provider/model-name
```
格式
```
model_settings
```
包含必填的
```
provider_type
```
字段
```
context_window_limit
```
在Agent层面设置，而非
```
model_settings
```
中
提供商专属设置使用正确的嵌套结构
对于自托管场景：已指定嵌入模型
Temperature取值在有效范围（0.0-2.0）内

Scripts

脚本工具

Model configuration:

```
scripts/basic_config.py
```
- Basic model configuration
```
scripts/basic_config.ts
```
- TypeScript equivalent
```
scripts/change_model.py
```
- Changing models on existing agents
```
scripts/provider_specific.py
```
- OpenAI reasoning, Anthropic thinking

Provider configuration:

```
scripts/setup_provider.py
```
- Add providers via REST API
```
scripts/validate_provider.py
```
- Check provider credentials
```
scripts/generate_env.py
```
- Generate .env for Docker

模型配置类：

```
scripts/basic_config.py
```
- 基础模型配置脚本
```
scripts/basic_config.ts
```
- TypeScript版本
```
scripts/change_model.py
```
- 为已有Agent更换模型的脚本
```
scripts/provider_specific.py
```
- OpenAI推理、Anthropic思维扩展配置脚本

提供商配置类：

```
scripts/setup_provider.py
```
- 通过REST API添加提供商的脚本
```
scripts/validate_provider.py
```
- 检查提供商凭证的脚本
```
scripts/generate_env.py
```
- 为Docker生成.env文件的脚本