elizaOS · shakkernerd · Jan 8, 2025 · Jan 8, 2025 · Jan 8, 2025 · Jan 8, 2025
diff --git a/.env.example b/.env.example
@@ -88,9 +88,6 @@ TWITTER_TARGET_USERS=           # Comma separated list of Twitter user names to
 TWITTER_RETRY_LIMIT=            # Maximum retry attempts for Twitter login
 TWITTER_SPACES_ENABLE=false     # Enable or disable Twitter Spaces logic
 
-XAI_API_KEY=
-XAI_MODEL=
-
 # Post Interval Settings (in minutes)
 POST_INTERVAL_MIN=              # Default: 90
 POST_INTERVAL_MAX=              # Default: 180
@@ -103,7 +100,6 @@ MAX_ACTIONS_PROCESSING=1 # Maximum number of actions (e.g., retweets, likes) to
 ACTION_TIMELINE_TYPE=foryou      # Type of timeline to interact with. Options: "foryou" or "following". Default: "foryou"
 
 # Feature Flags
-IMAGE_GEN=                      # Set to TRUE to enable image generation
 USE_OPENAI_EMBEDDING=           # Set to TRUE for OpenAI/1536, leave blank for local
 USE_OLLAMA_EMBEDDING=           # Set to TRUE for OLLAMA/1024, leave blank for local
 

diff --git a/README_CN.md b/README_CN.md
@@ -188,9 +188,6 @@ TWITTER_USERNAME= # Account username
 TWITTER_PASSWORD= # Account password
 TWITTER_EMAIL= # Account email
 
-XAI_API_KEY=
-XAI_MODEL=
-
 
 # For asking Claude stuff
 ANTHROPIC_API_KEY=

diff --git a/README_ES.md b/README_ES.md
@@ -54,15 +54,15 @@ Para evitar conflictos en el directorio central, se recomienda agregar acciones
 
 ### Ejecutar con Llama
 
-Puede ejecutar modelos Llama 70B o 405B configurando la variable de ambiente `XAI_MODEL` en `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo` o `meta-llama/Meta-Llama-3.1-405B-Instruct`
+Puede ejecutar modelos Llama 70B o 405B configurando la variable de ambiente para un proveedor que soporte estos modelos. Llama también es soportado localmente si no se configura otro proveedor.
 
 ### Ejecutar con Grok
 
-Puede ejecutar modelos Grok configurando la variable de ambiente `XAI_MODEL` en `grok-beta`
+Puede ejecutar modelos Grok configurando la variable de ambiente `GROK_API_KEY` y configurando "grok" como proveedor en el archivo de caracteres.
 
 ### Ejecutar con OpenAI
 
-Puede ejecutar modelos OpenAI configurando la variable de ambiente `XAI_MODEL` en `gpt-4o-mini` o `gpt-4o`
+Puede ejecutar modelos OpenAI configurando la variable de ambiente `OPENAI_API_KEY` y configurando "openai" como proveedor en el archivo de caracteres.
 
 ## Requisitos Adicionales
 
@@ -99,9 +99,6 @@ TWITTER_USERNAME= # Nombre de usuario de la cuenta
 TWITTER_PASSWORD= # Contraseña de la cuenta
 TWITTER_EMAIL= # Correo electrónico de la cuenta
 
-XAI_API_KEY=
-XAI_MODEL=
-
 # Para consultar a Claude
 ANTHROPIC_API_KEY=
 

diff --git a/agent/src/index.ts b/agent/src/index.ts
@@ -282,8 +282,6 @@ export function getTokenForProvider(
                 settings.LLAMACLOUD_API_KEY ||
                 character.settings?.secrets?.TOGETHER_API_KEY ||
                 settings.TOGETHER_API_KEY ||
-                character.settings?.secrets?.XAI_API_KEY ||
-                settings.XAI_API_KEY ||
                 character.settings?.secrets?.OPENAI_API_KEY ||
                 settings.OPENAI_API_KEY
             );

diff --git a/docs/README.md b/docs/README.md
@@ -59,15 +59,15 @@ To avoid git clashes in the core directory, we recommend adding custom actions t
 
 ### Run with Llama
 
-You can run Llama 70B or 405B models by setting the `XAI_MODEL` environment variable to `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo` or `meta-llama/Meta-Llama-3.1-405B-Instruct`
+You can run Llama 70B or 405B models by setting the environment variable for a provider that supports these models. Llama is also supported locally if no other provider is set.
 
 ### Run with Grok
 
-You can run Grok models by setting the `XAI_MODEL` environment variable to `grok-beta`
+You can run Grok models by setting the `GROK_API_KEY` environment variable to your Grok API key and setting grok as the model provider in your character file.
 
 ### Run with OpenAI
 
-You can run OpenAI models by setting the `XAI_MODEL` environment variable to `gpt-4-mini` or `gpt-4o`
+You can run OpenAI models by setting the `OPENAI_API_KEY` environment variable to your OpenAI API key and setting openai as the model provider in your character file.
 
 ## Additional Requirements
 
@@ -103,10 +103,6 @@ TWITTER_USERNAME= # Account username
 TWITTER_PASSWORD= # Account password
 TWITTER_EMAIL= # Account email
 
-X_SERVER_URL=
-XAI_API_KEY=
-XAI_MODEL=
-
 
 # For asking Claude stuff
 ANTHROPIC_API_KEY=
@@ -143,9 +139,7 @@ Make sure that you've installed the CUDA Toolkit, including cuDNN and cuBLAS.
 
 ### Running locally
 
-Add XAI_MODEL and set it to one of the above options from [Run with
-Llama](#run-with-llama) - you can leave X_SERVER_URL and XAI_API_KEY blank, it
-downloads the model from huggingface and queries it locally
+By default, the bot will download and use a local model. You can change this by setting the environment variables for the model you want to use.
 
 # Clients
 

diff --git a/docs/docs/api/index.md b/docs/docs/api/index.md
@@ -56,15 +56,15 @@ To avoid git clashes in the core directory, we recommend adding custom actions t
 
 ### Run with Llama
 
-You can run Llama 70B or 405B models by setting the `XAI_MODEL` environment variable to `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo` or `meta-llama/Meta-Llama-3.1-405B-Instruct`
+You can run Llama 70B or 405B models by setting the environment variable for a provider that supports these models. Llama is also supported locally if no other provider is set.
 
 ### Run with Grok
 
-You can run Grok models by setting the `XAI_MODEL` environment variable to `grok-beta`
+You can run Grok models by setting the `GROK_API_KEY` environment variable to your Grok API key
 
 ### Run with OpenAI
 
-You can run OpenAI models by setting the `XAI_MODEL` environment variable to `gpt-4o-mini` or `gpt-4o`
+You can run OpenAI models by setting the `OPENAI_API_KEY` environment variable to your OpenAI API key
 
 ## Additional Requirements
 
@@ -101,10 +101,6 @@ TWITTER_USERNAME= # Account username
 TWITTER_PASSWORD= # Account password
 TWITTER_EMAIL= # Account email
 
-X_SERVER_URL=
-XAI_API_KEY=
-XAI_MODEL=
-
 # For asking Claude stuff
 ANTHROPIC_API_KEY=
 
@@ -147,9 +143,7 @@ Make sure that you've installed the CUDA Toolkit, including cuDNN and cuBLAS.
 
 ### Running locally
 
-Add XAI_MODEL and set it to one of the above options from [Run with
-Llama](#run-with-llama) - you can leave X_SERVER_URL and XAI_API_KEY blank, it
-downloads the model from huggingface and queries it locally
+By default, the bot will download and use a local model. You can change this by setting the environment variables for the model you want to use.
 
 # Clients
 

diff --git a/docs/docs/guides/configuration.md b/docs/docs/guides/configuration.md
@@ -25,10 +25,6 @@ Here are the essential environment variables you need to configure:
 OPENAI_API_KEY=sk-your-key # Required for OpenAI features
 ANTHROPIC_API_KEY=your-key  # Required for Claude models
 TOGETHER_API_KEY=your-key   # Required for Together.ai models
-
-# Default Settings
-XAI_MODEL=gpt-4o-mini      # Default model to use
-X_SERVER_URL=              # Optional model API endpoint
 ```
 
 ### Client-Specific Configuration
@@ -74,11 +70,7 @@ HEURIST_API_KEY=
 
 # Livepeer Settings
 LIVEPEER_GATEWAY_URL=
-
-# Local Model Settings
-XAI_MODEL=meta-llama/Llama-3.1-7b-instruct
 ```
-
 ### Image Generation
 
 Configure image generation in your character file:

diff --git a/docs/docs/guides/local-development.md b/docs/docs/guides/local-development.md
@@ -75,8 +75,6 @@ Configure essential development variables:
 ```bash
 # Minimum required for local development
 OPENAI_API_KEY=sk-*           # Optional, for OpenAI features
-XAI_API_KEY=                 # Leave blank for local inference
-XAI_MODEL=meta-llama/Llama-3.1-7b-instruct  # Local model
 ```
 
 ### 5. Local Model Setup

diff --git a/docs/docs/quickstart.md b/docs/docs/quickstart.md
@@ -92,9 +92,9 @@ Eliza supports multiple AI models:
 - **Heurist**: Set `modelProvider: "heurist"` in your character file. Most models are uncensored.
     - LLM: Select available LLMs [here](https://docs.heurist.ai/dev-guide/supported-models#large-language-models-llms) and configure `SMALL_HEURIST_MODEL`,`MEDIUM_HEURIST_MODEL`,`LARGE_HEURIST_MODEL`
     - Image Generation: Select available Stable Diffusion or Flux models [here](https://docs.heurist.ai/dev-guide/supported-models#image-generation-models) and configure `HEURIST_IMAGE_MODEL` (default is FLUX.1-dev)
-- **Llama**: Set `XAI_MODEL=meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`
-- **Grok**: Set `XAI_MODEL=grok-beta`
-- **OpenAI**: Set `XAI_MODEL=gpt-4o-mini` or `gpt-4o`
+- **Llama**: Set `OLLAMA_MODEL` to your chosen model
+- **Grok**: Set `GROK_API_KEY` to your Grok API key and set `modelProvider: "grok"` in your character file
+- **OpenAI**: Set `OPENAI_API_KEY` to your OpenAI API key and set `modelProvider: "openai"` in your character file
 - **Livepeer**: Set `LIVEPEER_IMAGE_MODEL` to your chosen Livepeer image model, available models [here](https://livepeer-eliza.com/)
 
 You set which model to use inside the character JSON file
@@ -103,8 +103,6 @@ You set which model to use inside the character JSON file
 
     #### For llama_local inference:
 
-      1. Set `XAI_MODEL` to your chosen model
-      2. Leave `X_SERVER_URL` and `XAI_API_KEY` blank
       3. The system will automatically download the model from Hugging Face
       4. `LOCAL_LLAMA_PROVIDER` can be blank