diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 2c91906c9..04cb80b4d 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -141,7 +141,6 @@ Flowise support different environment variables to configure your instance. You
 | DATABASE_SSL                | Database connection overssl (When DATABASE_TYPE is postgre)                  | Boolean                                          | false                               |
 | SECRETKEY_PATH              | Location where encryption key (used to encrypt/decrypt credentials) is saved | String                                           | `your-path/Flowise/packages/server` |
 | FLOWISE_SECRETKEY_OVERWRITE | Encryption key to be used instead of the key stored in SECRETKEY_PATH        | String                                           |
-| LOCALAI_CHAT_MODELS         | JSON-encoded string representing an array of chat models for LocalAI. Each object in the array should have a 'label' and 'name' property. | String                                          | '[]' (Empty Array)                  |
 
 You can also specify the env variables when using `npx`. For example:
 
diff --git a/packages/components/nodes/chatmodels/ChatLocalAI/ChatLocalAI.ts b/packages/components/nodes/chatmodels/ChatLocalAI/ChatLocalAI.ts
index 258db1f80..c44f03ce1 100644
--- a/packages/components/nodes/chatmodels/ChatLocalAI/ChatLocalAI.ts
+++ b/packages/components/nodes/chatmodels/ChatLocalAI/ChatLocalAI.ts
@@ -33,9 +33,6 @@ class ChatLocalAI_ChatModels implements INode {
             credentialNames: ['LocalAIApi'],
             optional: true
         }
-
-        const modelOptions = JSON.parse(process.env.LOCALAI_CHAT_MODELS || '[]');
-        
         this.inputs = [
             {
                 label: 'Cache',
@@ -52,10 +49,8 @@ class ChatLocalAI_ChatModels implements INode {
             {
                 label: 'Model Name',
                 name: 'modelName',
-                type: 'options',
-                options: modelOptions,
-                default: modelOptions.length > 0 ? modelOptions[0].name : '',
-                optional: true
+                type: 'string',
+                placeholder: 'gpt4all-lora-quantized.bin'
             },
             {
                 label: 'Temperature',
@@ -99,22 +94,22 @@ class ChatLocalAI_ChatModels implements INode {
         const topP = nodeData.inputs?.topP as string
         const timeout = nodeData.inputs?.timeout as string
         const basePath = nodeData.inputs?.basePath as string
-        
         const credentialData = await getCredentialData(nodeData.credential ?? '', options)
-        const openAIApiKey = getCredentialParam('LocalAIApiKey', credentialData, nodeData)
+        const localAIApiKey = getCredentialParam('LocalAIApiKey', credentialData, nodeData)
 
         const cache = nodeData.inputs?.cache as BaseCache
 
-        const obj: Partial<OpenAIChatInput> & BaseLLMParams & { openAIApiKey?: string } = {
+        const obj: Partial<OpenAIChatInput> & BaseLLMParams & { localAIApiKey?: string } = {
             temperature: parseFloat(temperature),
             modelName,
-            openAIApiKey
+            openAIApiKey: 'sk-'
         }
 
         if (maxTokens) obj.maxTokens = parseInt(maxTokens, 10)
         if (topP) obj.topP = parseFloat(topP)
         if (timeout) obj.timeout = parseInt(timeout, 10)
         if (cache) obj.cache = cache
+        if (localAIApiKey) obj.openAIApiKey = localAIApiKey
 
         const model = new OpenAIChat(obj, { basePath })
 
diff --git a/packages/server/.env.example b/packages/server/.env.example
index 9b7be0ff8..6e746a4df 100644
--- a/packages/server/.env.example
+++ b/packages/server/.env.example
@@ -26,5 +26,3 @@ PORT=3000
 # LANGCHAIN_ENDPOINT=https://api.smith.langchain.com
 # LANGCHAIN_API_KEY=your_api_key
 # LANGCHAIN_PROJECT=your_project
-
-# LOCALAI_CHAT_MODELS='[{"label": "model1", "name": "model1"}, {"label": "model2", "name": "model2"}]'