Merge pull request #506 from Ninot1Quyi/New-Model-Support-Mercury

New model support: Mercury (diffusion large language models)

README.md

@@ -12,8 +12,7 @@ Do not connect this bot to public servers with coding enabled. This project allo
 
 - [Minecraft Java Edition](https://www.minecraft.net/en-us/store/minecraft-java-bedrock-edition-pc) (up to v1.21.1, recommend v1.21.1)
 - [Node.js Installed](https://nodejs.org/) (at least v18)
-- One of these: [OpenAI API Key](https://openai.com/blog/openai-api) | [Gemini API Key](https://aistudio.google.com/app/apikey) | [Anthropic API Key](https://docs.anthropic.com/claude/docs/getting-access-to-claude) | [Replicate API Key](https://replicate.com/) | [Hugging Face API Key](https://huggingface.co/) | [Groq API Key](https://console.groq.com/keys) | [Ollama Installed](https://ollama.com/download). | [Mistral API Key](https://docs.mistral.ai/getting-started/models/models_overview/) | [Qwen API Key [Intl.]](https://www.alibabacloud.com/help/en/model-studio/developer-reference/get-api-key)/[[cn]](https://help.aliyun.com/zh/model-studio/getting-started/first-api-call-to-qwen?) | [Novita AI API Key](https://novita.ai/settings?utm_source=github_mindcraft&utm_medium=github_readme&utm_campaign=link#key-management) | [Cerebras API Key](https://cloud.cerebras.ai)
-
+- One of these: [OpenAI API Key](https://openai.com/blog/openai-api) | [Gemini API Key](https://aistudio.google.com/app/apikey) | [Anthropic API Key](https://docs.anthropic.com/claude/docs/getting-access-to-claude) | [Replicate API Key](https://replicate.com/) | [Hugging Face API Key](https://huggingface.co/) | [Groq API Key](https://console.groq.com/keys) | [Ollama Installed](https://ollama.com/download). | [Mistral API Key](https://docs.mistral.ai/getting-started/models/models_overview/) | [Qwen API Key [Intl.]](https://www.alibabacloud.com/help/en/model-studio/developer-reference/get-api-key)/[[cn]](https://help.aliyun.com/zh/model-studio/getting-started/first-api-call-to-qwen?) | [Novita AI API Key](https://novita.ai/settings?utm_source=github_mindcraft&utm_medium=github_readme&utm_campaign=link#key-management) | [Cerebras API Key](https://cloud.cerebras.ai) | [Mercury API](https://platform.inceptionlabs.ai/docs)
 
 ## Install and Run
 
@@ -66,6 +65,7 @@ You can configure the agent's name, model, and prompts in their profile like `an
 | `hyperbolic` | `HYPERBOLIC_API_KEY` | `hyperbolic/deepseek-ai/DeepSeek-V3` | [docs](https://docs.hyperbolic.xyz/docs/getting-started) |
 | `vllm` | n/a | `vllm/llama3` | n/a |
 | `cerebras` | `CEREBRAS_API_KEY` | `cerebras/llama-3.3-70b` | [docs](https://inference-docs.cerebras.ai/introduction) |
+| `mercury(EA)` | `MERCURY_API_KEY` | `mercury-coder-small` | [docs](https://www.inceptionlabs.ai/) |
 
 If you use Ollama, to install the models used by default (generation and embedding), execute the following terminal command:
 `ollama pull llama3.1 && ollama pull nomic-embed-text`

keys.example.json

@@ -14,5 +14,6 @@
     "HYPERBOLIC_API_KEY": "",
     "NOVITA_API_KEY": "",
     "OPENROUTER_API_KEY": "",
-    "CEREBRAS_API_KEY": ""
+    "CEREBRAS_API_KEY": "",
+    "MERCURY_API_KEY":""
 }

profiles/mercury.json

@@ -0,0 +1,15 @@
+{
+    "name": "Mercury",
+
+    "cooldown": 5000,
+
+    "model": {
+        "api": "mercury",
+        "url": "https://api.inceptionlabs.ai/v1",
+        "model": "mercury-coder-small"
+    },
+
+     "embedding": "openai",
+
+     "description":"Official Website Introduction：The world’s first diffusion large language models"
+}

settings.js

@@ -18,6 +18,7 @@ const settings = {
         // "./profiles/grok.json",
         // "./profiles/mistral.json",
         // "./profiles/deepseek.json",
+        //"./profiles/mercury.json",
 
         // using more than 1 profile requires you to /msg each bot indivually
         // individual profiles override values from the base profile

src/models/mercury.js

@@ -0,0 +1,92 @@
+import OpenAIApi from 'openai';
+import { getKey, hasKey } from '../utils/keys.js';
+import { strictFormat } from '../utils/text.js';
+
+export class Mercury {
+    constructor(model_name, url, params) {
+        this.model_name = model_name;
+        this.params = params;
+        let config = {};
+        if (url)
+            config.baseURL = url;
+
+        config.apiKey = getKey('MERCURY_API_KEY');
+
+        this.openai = new OpenAIApi(config);
+    }
+
+    async sendRequest(turns, systemMessage, stop_seq='***') {
+        if (typeof stop_seq === 'string') {
+            stop_seq = [stop_seq];
+        } else if (!Array.isArray(stop_seq)) {
+            stop_seq = [];
+        }
+        let messages = [{'role': 'system', 'content': systemMessage}].concat(turns);
+        messages = strictFormat(messages);
+        const pack = {
+            model: this.model_name || "mercury-coder-small",
+            messages,
+            stop: stop_seq,
+            ...(this.params || {})
+        };
+
+
+        let res = null;
+
+        try {
+            console.log('Awaiting mercury api response from model', this.model_name)
+            // console.log('Messages:', messages);
+            let completion = await this.openai.chat.completions.create(pack);
+            if (completion.choices[0].finish_reason == 'length')
+                throw new Error('Context length exceeded'); 
+            console.log('Received.')
+            res = completion.choices[0].message.content;
+        }
+        catch (err) {
+            if ((err.message == 'Context length exceeded' || err.code == 'context_length_exceeded') && turns.length > 1) {
+                console.log('Context length exceeded, trying again with shorter context.');
+                return await this.sendRequest(turns.slice(1), systemMessage, stop_seq);
+            } else if (err.message.includes('image_url')) {
+                console.log(err);
+                res = 'Vision is only supported by certain models.';
+            } else {
+                console.log(err);
+                res = 'My brain disconnected, try again.';
+            }
+        }
+        return res;
+    }
+
+    async sendVisionRequest(messages, systemMessage, imageBuffer) {
+        const imageMessages = [...messages];
+        imageMessages.push({
+            role: "user",
+            content: [
+                { type: "text", text: systemMessage },
+                {
+                    type: "image_url",
+                    image_url: {
+                        url: `data:image/jpeg;base64,${imageBuffer.toString('base64')}`
+                    }
+                }
+            ]
+        });
+        
+        return this.sendRequest(imageMessages, systemMessage);
+    }
+
+    async embed(text) {
+        if (text.length > 8191)
+            text = text.slice(0, 8191);
+        const embedding = await this.openai.embeddings.create({
+            model: this.model_name || "text-embedding-3-small",
+            input: text,
+            encoding_format: "float",
+        });
+        return embedding.data[0].embedding;
+    }
+
+}
+
+
+

src/models/prompter.js

@@ -228,7 +228,7 @@ export class Prompter {
                     console.error('Error: Generated response is not a string', generation);
                     throw new Error('Generated response is not a string');
                 }
-                console.log("Generated response:", generation); 
+                console.log("Generated response:", generation);
                 await this._saveLog(prompt, messages, generation, 'conversation');
 
             } catch (error) {
@@ -245,7 +245,7 @@ export class Prompter {
             if (current_msg_time !== this.most_recent_msg_time) {
                 console.warn(`${this.agent.name} received new message while generating, discarding old response.`);
                 return '';
-            } 
+            }
 
             if (generation?.includes('</think>')) {
                 const [_, afterThink] = generation.split('</think>')
@@ -282,7 +282,7 @@ export class Prompter {
         await this._saveLog(prompt, to_summarize, resp, 'memSaving');
         if (resp?.includes('</think>')) {
             const [_, afterThink] = resp.split('</think>')
-            resp = afterThink
+            resp = afterThink;
         }
         return resp;
     }