Merge pull request #2 from Titan-Node/livepeer-doc-updates

Updated docs for Livepeer LLM integration

Author: UD1sto

.env.example

@@ -128,7 +128,7 @@ LARGE_HYPERBOLIC_MODEL=         # Default: meta-llama/Meta-Llama-3.1-405-Instruc
  LARGE_AKASH_CHAT_API_MODEL=  # Default: Meta-Llama-3-1-405B-Instruct-FP8
 
 # Livepeer configuration
-LIVEPEER_GATEWAY_URL=           # Free inference gateways and docs: https://livepeer-eliza.com/
+LIVEPEER_GATEWAY_URL=https://dream-gateway.livepeer.cloud           # Free inference gateways and docs: https://livepeer-eliza.com/
 LIVEPEER_IMAGE_MODEL=           # Default: ByteDance/SDXL-Lightning
 LIVEPEER_SMALL_MODEL=
 LIVEPEER_MEDIUM_MODEL=

docs/docs/advanced/fine-tuning.md

@@ -26,6 +26,7 @@ enum ModelProviderName {
     REDPILL,
     OPENROUTER,
     HEURIST,
+  LIVEPEER,
 }
 ```
 
@@ -272,24 +273,45 @@ const llamaLocalSettings = {
 
 ```typescript
 const heuristSettings = {
-    settings: {
-        stop: [],
-        maxInputTokens: 32768,
-        maxOutputTokens: 8192,
-        repetition_penalty: 0.0,
-        temperature: 0.7,
-    },
-    imageSettings: {
-        steps: 20,
-    },
-    endpoint: "https://llm-gateway.heurist.xyz",
-    model: {
-        [ModelClass.SMALL]: "hermes-3-llama3.1-8b",
-        [ModelClass.MEDIUM]: "mistralai/mixtral-8x7b-instruct",
-        [ModelClass.LARGE]: "nvidia/llama-3.1-nemotron-70b-instruct",
-        [ModelClass.EMBEDDING]: "", // Add later
-        [ModelClass.IMAGE]: "FLUX.1-dev",
-    },
+  settings: {
+    stop: [],
+    maxInputTokens: 32768,
+    maxOutputTokens: 8192,
+    repetition_penalty: 0.0,
+    temperature: 0.7,
+  },
+  imageSettings: {
+    steps: 20,
+  },
+  endpoint: "https://llm-gateway.heurist.xyz",
+  model: {
+    [ModelClass.SMALL]: "hermes-3-llama3.1-8b",
+    [ModelClass.MEDIUM]: "mistralai/mixtral-8x7b-instruct",
+    [ModelClass.LARGE]: "nvidia/llama-3.1-nemotron-70b-instruct",
+    [ModelClass.EMBEDDING]: "", // Add later
+    [ModelClass.IMAGE]: "FLUX.1-dev",
+  },
+};
+```
+
+### Livepeer Provider
+
+```typescript
+const livepeerSettings = {
+  settings: {
+    stop: [],
+    maxInputTokens: 128000,
+    maxOutputTokens: 8192,
+    repetition_penalty: 0.4,
+    temperature: 0.7,
+  },
+  endpoint: "https://dream-gateway.livepeer.cloud",
+  model: {
+    [ModelClass.SMALL]: "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    [ModelClass.MEDIUM]: "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    [ModelClass.LARGE]: "meta-llama/Llama-3.3-70B-Instruct",
+    [ModelClass.IMAGE]: "ByteDance/SDXL-Lightning",
+  },
 };
 ```
 

docs/docs/core/characterfile.md

@@ -92,7 +92,7 @@ The character's display name for identification and in conversations.
 
 #### `modelProvider` (required)
 
-Specifies the AI model provider. Supported options from [ModelProviderName](/api/enumerations/modelprovidername) include `anthropic`, `llama_local`, `openai`, and others.
+Specifies the AI model provider. Supported options from [ModelProviderName](/api/enumerations/modelprovidername) include `anthropic`, `llama_local`, `openai`, `livepeer`, and others.
 
 #### `clients` (required)
 

docs/docs/quickstart.md

@@ -92,10 +92,17 @@ 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)
+<<<<<<< HEAD
 - **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/)
+=======
+- **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`
+- **Livepeer**: Set `SMALL_LIVEPEER_MODEL`,`MEDIUM_LIVEPEER_MODEL`,`LARGE_LIVEPEER_MODEL` and `LIVEPEER_IMAGE_MODEL` to your desired models listed [here](https://livepeer-eliza.com/).
+>>>>>>> 95f56e6b4 (Merge pull request #2 from Titan-Node/livepeer-doc-updates)
 
 You set which model to use inside the character JSON file