diff --git a/Cargo.lock b/Cargo.lock
index 3246022..709cf0d 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1954,7 +1954,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
 [[package]]
 name = "pgml"
-version = "1.0.0"
+version = "1.0.1"
 dependencies = [
  "anyhow",
  "async-trait",
diff --git a/Cargo.toml b/Cargo.toml
index 462777b..6aeec46 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -8,7 +8,6 @@ edition = "2021"
 [dependencies]
 anyhow = "1.0.75"
 lsp-server = "0.7.6"
-# lsp-server = { path = "../rust-analyzer/lib/lsp-server" }
 lsp-types = "0.95.0"
 ropey = "1.6.1"
 serde = "1.0.190"
diff --git a/editors/vscode/package.json b/editors/vscode/package.json
index b5ffcdf..2603435 100644
--- a/editors/vscode/package.json
+++ b/editors/vscode/package.json
@@ -17,12 +17,8 @@
   "contributes": {
     "commands": [
       {
-        "command": "lsp-ai.generate",
-        "title": "LSP AI Generate"
-      },
-      {
-        "command": "lsp-ai.generateStream",
-        "title": "LSP AI Generate Stream"
+        "command": "lsp-ai.generation",
+        "title": "LSP-AI Generation"
       }
     ],
     "configuration": {
diff --git a/editors/vscode/src/index.ts b/editors/vscode/src/index.ts
index 4e108ee..fe5452e 100644
--- a/editors/vscode/src/index.ts
+++ b/editors/vscode/src/index.ts
@@ -33,7 +33,7 @@ export function activate(context: vscode.ExtensionContext) {
   client.start();
 
   // Register generate function
-  const generateCommand = 'lsp-ai.generate';
+  const generateCommand = 'lsp-ai.generation';
   const generateCommandHandler = (editor: vscode.TextEditor) => {
     let params = {
       textDocument: {
@@ -41,7 +41,7 @@ export function activate(context: vscode.ExtensionContext) {
       },
       position: editor.selection.active
     };
-    client.sendRequest("textDocument/generate", params).then(result => {
+    client.sendRequest("textDocument/generation", params).then(result => {
       editor.edit((edit) => {
         edit.insert(editor.selection.active, result["generatedText"]);
       });
@@ -51,29 +51,6 @@ export function activate(context: vscode.ExtensionContext) {
   };
   context.subscriptions.push(vscode.commands.registerTextEditorCommand(generateCommand, generateCommandHandler));
 
-  // Register functions
-  // This function is not ready to go
-  // const generateStreamCommand = 'lsp-ai.generateStream';
-  // const generateStreamCommandHandler = (editor: vscode.TextEditor) => {
-  //   let params = {
-  //     textDocument: {
-  //       uri: editor.document.uri.toString(),
-  //     },
-  //     position: editor.selection.active,
-  //     partialResultToken: uuidv4()
-  //   };
-  //   console.log("PARAMS: ", params);
-  //   client.sendRequest("textDocument/generateStream", params).then(result => {
-  //     console.log("RECEIVED RESULT", result);
-  //     editor.edit((edit) => {
-  //       edit.insert(editor.selection.active, result["generatedText"]);
-  //     });
-  //   }).catch(error => {
-  //     console.error("Error making generate request", error);
-  //   });
-  // };
-  // context.subscriptions.push(vscode.commands.registerTextEditorCommand(generateStreamCommand, generateStreamCommandHandler));
-
   vscode.languages.registerInlineCompletionItemProvider({ pattern: '**' },
     {
       provideInlineCompletionItems: async (document: vscode.TextDocument, position: vscode.Position) => {
@@ -83,7 +60,7 @@ export function activate(context: vscode.ExtensionContext) {
           },
           position: position
         };
-        const result = await client.sendRequest("textDocument/generate", params);
+        const result = await client.sendRequest("textDocument/generation", params);
         return [new vscode.InlineCompletionItem(result["generatedText"])];
       }
     }
diff --git a/src/config.rs b/src/config.rs
index 5b5bedb..f95d747 100644
--- a/src/config.rs
+++ b/src/config.rs
@@ -6,8 +6,8 @@ use std::collections::HashMap;
 const DEFAULT_LLAMA_CPP_N_CTX: usize = 1024;
 const DEFAULT_OPENAI_MAX_CONTEXT: usize = 2048;
 
-const DEFAULT_MAX_COMPLETION_TOKENS: usize = 32;
-const DEFAULT_MAX_GENERATION_TOKENS: usize = 256;
+const DEFAULT_MAX_COMPLETION_TOKENS: usize = 16;
+const DEFAULT_MAX_GENERATION_TOKENS: usize = 64;
 
 pub type Kwargs = HashMap<String, Value>;
 
@@ -263,7 +263,7 @@ impl Config {
 
     pub fn get_transformer_max_requests_per_second(&self) -> f32 {
         match &self.config.transformer {
-            ValidTransformerBackend::LLaMACPP(_) => f32::MAX,
+            ValidTransformerBackend::LLaMACPP(_) => 1.,
             ValidTransformerBackend::OpenAI(openai) => openai.max_requests_per_second,
             ValidTransformerBackend::Anthropic(anthropic) => anthropic.max_requests_per_second,
         }
diff --git a/submodules/postgresml b/submodules/postgresml
index a16ff70..47610cb 160000
--- a/submodules/postgresml
+++ b/submodules/postgresml
@@ -1 +1 @@
-Subproject commit a16ff700c1d54582711d14c2f57341bb9bd82be2
+Subproject commit 47610cb174df8120fbc5255b221aa49a2484de6a