Feat #748 custom instruction merge with main

Author: KartikGS

.env

@@ -109,7 +109,9 @@ PUBLIC_ANNOUNCEMENT_BANNERS=`[
 
 PARQUET_EXPORT_DATASET=
 PARQUET_EXPORT_HF_TOKEN=
-PARQUET_EXPORT_SECRET=
+ADMIN_API_SECRET=# secret to admin API calls, like computing usage stats or exporting parquet data
+
+PARQUET_EXPORT_SECRET=#DEPRECATED, use ADMIN_API_SECRET instead
 
 RATE_LIMIT= # requests per minute
 MESSAGES_BEFORE_LOGIN=# how many messages a user can send in a conversation before having to login. set to 0 to force login right away

.env.template

@@ -4,7 +4,9 @@ MODELS=`[
     {
     "name" : "mistralai/Mixtral-8x7B-Instruct-v0.1",
     "description" : "The latest MoE model from Mistral AI! 8x7B and outperforms Llama 2 70B in most benchmarks.",
+    "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png",
     "websiteUrl" : "https://mistral.ai/news/mixtral-of-experts/",
+    "modelUrl": "https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1",
     "preprompt" : "",
     "chatPromptTemplate": "<s> {{#each messages}}{{#ifUser}}[INST]{{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}} {{content}} [/INST]{{/ifUser}}{{#ifAssistant}} {{content}}</s> {{/ifAssistant}}{{/each}}",
     "parameters" : {
@@ -29,10 +31,39 @@ MODELS=`[
       }
     ]
   },
-    {
+  {
+    "name" : "google/gemma-7b-it",
+    "description": "Gemma 7B belongs to a family of lightweight models built by Google, based on the same research and technology used to create the Gemini models.",
+    "websiteUrl" : "https://blog.google/technology/developers/gemma-open-models/",
+    "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/google-logo.png",
+    "modelUrl": "https://huggingface.co/google/gemma-7b-it",
+    "preprompt": "",
+    "chatPromptTemplate" : "{{#each messages}}{{#ifUser}}<start_of_turn>user\n{{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}}<end_of_turn>\n<start_of_turn>model\n{{/ifUser}}{{#ifAssistant}}{{content}}<end_of_turn>\n{{/ifAssistant}}{{/each}}",
+    "promptExamples": [
+      {
+        "title": "Write an email from bullet list",
+        "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+      }, {
+        "title": "Code a snake game",
+        "prompt": "Code a basic snake game in python, give explanations for each step."
+      }, {
+        "title": "Assist in a task",
+        "prompt": "How do I make a delicious lemon cheesecake?"
+      }
+    ],
+    "parameters": {
+        "do_sample": true,
+        "truncate": 7168,
+        "max_new_tokens": 1024,
+        "stop" : ["<end_of_turn>"]
+      }
+  },
+  {
       "name": "meta-llama/Llama-2-70b-chat-hf",
       "description": "The latest and biggest model from Meta, fine-tuned for chat.",
+      "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/meta-logo.png",
       "websiteUrl": "https://ai.meta.com/llama/",
+      "modelUrl": "https://huggingface.co/meta-llama/Llama-2-70b-chat-hf",
       "preprompt": " ",
       "chatPromptTemplate" : "<s>[INST] <<SYS>>\n{{preprompt}}\n<</SYS>>\n\n{{#each messages}}{{#ifUser}}{{content}} [/INST] {{/ifUser}}{{#ifAssistant}}{{content}} </s><s>[INST] {{/ifAssistant}}{{/each}}",
       "promptExamples": [
@@ -60,7 +91,9 @@ MODELS=`[
     {
       "name" : "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
       "description" : "Nous Hermes 2 Mixtral 8x7B DPO is the new flagship Nous Research model trained over the Mixtral 8x7B MoE LLM.",
+      "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nous-logo.png",
       "websiteUrl" : "https://nousresearch.com/",
+      "modelUrl": "https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
       "chatPromptTemplate" : "{{#if @root.preprompt}}<|im_start|>system\n{{@root.preprompt}}<|im_end|>\n{{/if}}{{#each messages}}{{#ifUser}}<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n{{/ifUser}}{{#ifAssistant}}{{content}}<|im_end|>\n{{/ifAssistant}}{{/each}}",
       "promptExamples": [
         {
@@ -88,7 +121,9 @@ MODELS=`[
       "name": "codellama/CodeLlama-70b-Instruct-hf",
       "displayName": "codellama/CodeLlama-70b-Instruct-hf",
       "description": "Code Llama, a state of the art code model from Meta. Now in 70B!",
+      "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/meta-logo.png",
       "websiteUrl": "https://ai.meta.com/blog/code-llama-large-language-model-coding/",
+      "modelUrl": "https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf",
       "preprompt": "",
       "chatPromptTemplate" : "<s>{{#if @root.preprompt}}Source: system\n\n {{@root.preprompt}} <step> {{/if}}{{#each messages}}{{#ifUser}}Source: user\n\n {{content}} <step> {{/ifUser}}{{#ifAssistant}}Source: assistant\n\n {{content}} <step> {{/ifAssistant}}{{/each}}Source: assistant\nDestination: user\n\n ",
       "promptExamples": [
@@ -117,7 +152,9 @@ MODELS=`[
       "name": "mistralai/Mistral-7B-Instruct-v0.1",
       "displayName": "mistralai/Mistral-7B-Instruct-v0.1",
       "description": "Mistral 7B is a new Apache 2.0 model, released by Mistral AI that outperforms Llama2 13B in benchmarks.",
+      "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png",
       "websiteUrl": "https://mistral.ai/news/announcing-mistral-7b/",
+      "modelUrl": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1",
       "preprompt": "",
       "chatPromptTemplate" : "<s>{{#each messages}}{{#ifUser}}[INST] {{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}} [/INST]{{/ifUser}}{{#ifAssistant}}{{content}}</s>{{/ifAssistant}}{{/each}}",
       "parameters": {
@@ -147,7 +184,9 @@ MODELS=`[
       "name": "mistralai/Mistral-7B-Instruct-v0.2",
       "displayName": "mistralai/Mistral-7B-Instruct-v0.2",
       "description": "Mistral 7B is a new Apache 2.0 model, released by Mistral AI that outperforms Llama2 13B in benchmarks.",
+      "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png",
       "websiteUrl": "https://mistral.ai/news/announcing-mistral-7b/",
+      "modelUrl": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2",
       "preprompt": "",
       "chatPromptTemplate" : "<s>{{#each messages}}{{#ifUser}}[INST] {{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}} [/INST]{{/ifUser}}{{#ifAssistant}}{{content}}</s>{{/ifAssistant}}{{/each}}",
       "parameters": {
@@ -176,7 +215,9 @@ MODELS=`[
     "name": "openchat/openchat-3.5-0106",
     "displayName": "openchat/openchat-3.5-0106",
     "description": "OpenChat 3.5 is the #1 model on MT-Bench, with only 7B parameters.",
+    "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/openchat-logo.png",
     "websiteUrl": "https://huggingface.co/openchat/openchat-3.5-0106",
+    "modelUrl": "https://huggingface.co/openchat/openchat-3.5-0106",
     "preprompt": "",
     "chatPromptTemplate" : "<s>{{#each messages}}{{#ifUser}}GPT4 Correct User: {{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}}<|end_of_turn|>GPT4 Correct Assistant:{{/ifUser}}{{#ifAssistant}}{{content}}<|end_of_turn|>{{/ifAssistant}}{{/each}}",
     "parameters": {

.github/workflows/deploy-release.yml

@@ -26,6 +26,7 @@ jobs:
           MONGODB_URL: ${{ secrets.MONGODB_URL }}
           HF_DEPLOYMENT_TOKEN: ${{ secrets.HF_DEPLOYMENT_TOKEN }}
           WEBHOOK_URL_REPORT_ASSISTANT: ${{ secrets.WEBHOOK_URL_REPORT_ASSISTANT }}
+          ADMIN_API_SECRET: ${{ secrets.ADMIN_API_SECRET }}
         run: npm run updateProdEnv
   sync-to-hub:
     runs-on: ubuntu-latest

PROMPTS.md

@@ -61,3 +61,9 @@ System: {{preprompt}}\nUser:{{#each messages}}{{#ifUser}}{{content}}\nFalcon:{{/
 ```env
 <s>{{#if @root.preprompt}}Source: system\n\n {{@root.preprompt}} <step> {{/if}}{{#each messages}}{{#ifUser}}Source: user\n\n {{content}} <step> {{/ifUser}}{{#ifAssistant}}Source: assistant\n\n {{content}} <step> {{/ifAssistant}}{{/each}}Source: assistant\nDestination: user\n\n ``
 ```
+
+## Gemma
+
+```env
+{{#each messages}}{{#ifUser}}<start_of_turn>user\n{{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}}<end_of_turn>\n<start_of_turn>model\n{{/ifUser}}{{#ifAssistant}}{{content}}<end_of_turn>\n{{/ifAssistant}}{{/each}}
+```

README.md

@@ -616,3 +616,37 @@ npm run updateLocalEnv
 ```
 
 This will replace your `.env.local` file with the one that will be used in prod (simply taking `.env.template + .env.SECRET_CONFIG`).
+
+### Populate database
+
+> [!WARNING]  
+> The `MONGODB_URL` used for this script will be fetched from `.env.local`. Make sure it's correct! The command runs directly on the database.
+
+You can populate the database using faker data using the `populate` script:
+
+```bash
+npm run populate <flags here>
+```
+
+At least one flag must be specified, the following flags are available:
+
+- `reset` - resets the database
+- `all` - populates all tables
+- `users` - populates the users table
+- `settings` - populates the settings table for existing users
+- `assistants` - populates the assistants table for existing users
+- `conversations` - populates the conversations table for existing users
+
+For example, you could use it like so:
+
+```bash
+npm run populate reset
+```
+
+to clear out the database. Then login in the app to create your user and run the following command:
+
+```bash
+npm run populate users settings assistants conversations
+```
+
+to populate the database with fake data, including fake conversations and assistants for your user.