diff --git a/src/khoj/interface/web/chat.html b/src/khoj/interface/web/chat.html
index 4450646b..c5f4b703 100644
--- a/src/khoj/interface/web/chat.html
+++ b/src/khoj/interface/web/chat.html
@@ -9,6 +9,7 @@
         <link rel="stylesheet" href="/static/assets/khoj.css">
     </head>
     <script>
+        let chatOptions = [];
         function copyProgrammaticOutput(event) {
             // Remove the first 4 characters which are the "Copy" button
             const programmaticOutput = event.target.parentNode.textContent.trim().slice(4);
@@ -109,6 +110,9 @@
                     const reader = response.body.getReader();
                     const decoder = new TextDecoder();
 
+                    let chatTooltip = document.getElementById("chat-tooltip");
+                    chatTooltip.style.display = "none";
+
                     function readStream() {
                         reader.read().then(({ done, value }) => {
                             if (done) {
@@ -159,6 +163,35 @@
             }
         }
 
+        function onChatInput() {
+            let chatInput = document.getElementById("chat-input");
+            if (chatInput.value === "/") {
+                let chatTooltip = document.getElementById("chat-tooltip");
+                chatTooltip.style.display = "block";
+                let helpText = "<div>";
+                for (let key in chatOptions) {
+                    helpText += "<b>/" + key + "</b>: " + chatOptions[key] + "<br>";
+                }
+                chatTooltip.innerHTML = helpText;
+            } else if (chatInput.value.startsWith("/")) {
+                const firstWord = chatInput.value.split(" ")[0];
+                if (firstWord.substring(1) in chatOptions) {
+                    // Add a div element around the text.
+                    let chatTooltip = document.getElementById("chat-tooltip");
+                    chatTooltip.style.display = "block";
+                    chatTooltip.innerHTML = "Mode: " + firstWord.substring(1);
+                } else {
+                    let chatTooltip = document.getElementById("chat-tooltip");
+                    chatTooltip.style.display = "none";
+                }
+            } else {
+                let chatTooltip = document.getElementById("chat-tooltip");
+                chatTooltip.style.display = "none";
+            }
+
+            autoResize();
+        }
+
         function autoResize() {
             const textarea = document.getElementById('chat-input');
             const scrollTop = textarea.scrollTop;
@@ -196,6 +229,18 @@
                     return;
                 });
 
+            fetch('/api/chat/options')
+                .then(response => response.json())
+                .then(data => {
+                    // Render chat options, if any
+                    if (data) {
+                        chatOptions = data;
+                    }
+                })
+                .catch(err => {
+                    return;
+                });
+
             // Fill query field with value passed in URL query parameters, if any.
             var query_via_url = new URLSearchParams(window.location.search).get("q");
             if (query_via_url) {
@@ -242,7 +287,8 @@
 
         <!-- Chat Footer -->
         <div id="chat-footer">
-            <textarea id="chat-input" class="option" oninput="autoResize()" onkeyup=incrementalChat(event) autofocus="autofocus" placeholder="What is the meaning of life?"></textarea>
+            <div id="chat-tooltip" style="display: none;"></div>
+            <textarea id="chat-input" class="option" oninput="onChatInput()" onkeyup=incrementalChat(event) autofocus="autofocus" placeholder="What is the meaning of life?"></textarea>
         </div>
     </body>
 
@@ -450,6 +496,10 @@
             padding: 10px;
         }
 
+        div#chat-tooltip {
+            text-align: left;
+        }
+
         @keyframes gradient {
             0% {
                 background-position: 0% 50%;
@@ -509,7 +559,7 @@
         khojBannerSubmit?.addEventListener("click", function(event) {
             event.preventDefault();
             var email = document.getElementById("khoj-banner-email").value;
-            fetch("https://lantern.khoj.dev/beta/users/", {
+            fetch("https://app.khoj.dev/beta/users/", {
                     method: "POST",
                     body: JSON.stringify({
                         email: email
diff --git a/src/khoj/interface/web/index.html b/src/khoj/interface/web/index.html
index 9c7646dc..b0956f14 100644
--- a/src/khoj/interface/web/index.html
+++ b/src/khoj/interface/web/index.html
@@ -467,7 +467,7 @@
         khojBannerSubmit?.addEventListener("click", function(event) {
             event.preventDefault();
             var email = document.getElementById("khoj-banner-email").value;
-            fetch("https://lantern.khoj.dev/beta/users/", {
+            fetch("https://app.khoj.dev/beta/users/", {
                     method: "POST",
                     body: JSON.stringify({
                         email: email
diff --git a/src/khoj/main.py b/src/khoj/main.py
index 70976454..f3011b2e 100644
--- a/src/khoj/main.py
+++ b/src/khoj/main.py
@@ -14,6 +14,7 @@ import threading
 import warnings
 from platform import system
 import webbrowser
+from importlib.metadata import version
 
 # Ignore non-actionable warnings
 warnings.filterwarnings("ignore", message=r"snapshot_download.py has been made private", category=FutureWarning)
@@ -153,6 +154,7 @@ def set_state(args):
     state.host = args.host
     state.port = args.port
     state.demo = args.demo
+    state.khoj_version = version("khoj-assistant")
 
 
 def start_server(app, host=None, port=None, socket=None):
diff --git a/src/khoj/processor/conversation/gpt4all/chat_model.py b/src/khoj/processor/conversation/gpt4all/chat_model.py
index 1e286cd2..d3dd9bf5 100644
--- a/src/khoj/processor/conversation/gpt4all/chat_model.py
+++ b/src/khoj/processor/conversation/gpt4all/chat_model.py
@@ -1,4 +1,4 @@
-from typing import Union, List
+from typing import Iterator, Union, List
 from datetime import datetime
 import logging
 from threading import Thread
@@ -11,6 +11,7 @@ from khoj.processor.conversation.utils import ThreadedGenerator, generate_chatml
 from khoj.processor.conversation import prompts
 from khoj.utils.constants import empty_escape_sequences
 from khoj.utils import state
+from khoj.utils.helpers import ConversationCommand, is_none_or_empty
 
 logger = logging.getLogger(__name__)
 
@@ -118,7 +119,8 @@ def converse_offline(
     model: str = "llama-2-7b-chat.ggmlv3.q4_K_S.bin",
     loaded_model: Union[GPT4All, None] = None,
     completion_func=None,
-) -> ThreadedGenerator:
+    conversation_command=ConversationCommand.Notes,
+) -> Union[ThreadedGenerator, Iterator[str]]:
     """
     Converse with user using Llama
     """
@@ -127,8 +129,10 @@ def converse_offline(
     compiled_references_message = "\n\n".join({f"{item}" for item in references})
 
     # Get Conversation Primer appropriate to Conversation Type
-    if compiled_references_message == "":
+    if conversation_command == ConversationCommand.General:
         conversation_primer = user_query
+    elif conversation_command == ConversationCommand.Notes and is_none_or_empty(compiled_references_message):
+        return iter([prompts.no_notes_found.format()])
     else:
         conversation_primer = prompts.notes_conversation_llamav2.format(
             query=user_query, references=compiled_references_message
diff --git a/src/khoj/processor/conversation/openai/gpt.py b/src/khoj/processor/conversation/openai/gpt.py
index bf391f09..02e7a742 100644
--- a/src/khoj/processor/conversation/openai/gpt.py
+++ b/src/khoj/processor/conversation/openai/gpt.py
@@ -14,6 +14,7 @@ from khoj.processor.conversation.openai.utils import (
     completion_with_backoff,
 )
 from khoj.processor.conversation.utils import generate_chatml_messages_with_context
+from khoj.utils.helpers import ConversationCommand, is_none_or_empty
 
 
 logger = logging.getLogger(__name__)
@@ -108,6 +109,7 @@ def converse(
     api_key: Optional[str] = None,
     temperature: float = 0.2,
     completion_func=None,
+    conversation_command=ConversationCommand.Notes,
 ):
     """
     Converse with user using OpenAI's ChatGPT
@@ -117,8 +119,10 @@ def converse(
     compiled_references = "\n\n".join({f"# {item}" for item in references})
 
     # Get Conversation Primer appropriate to Conversation Type
-    if compiled_references == "":
+    if conversation_command == ConversationCommand.General:
         conversation_primer = prompts.general_conversation.format(current_date=current_date, query=user_query)
+    elif conversation_command == ConversationCommand.Notes and is_none_or_empty(compiled_references):
+        return iter([prompts.no_notes_found.format()])
     else:
         conversation_primer = prompts.notes_conversation.format(
             current_date=current_date, query=user_query, references=compiled_references
diff --git a/src/khoj/processor/conversation/prompts.py b/src/khoj/processor/conversation/prompts.py
index 566e94c1..79718ade 100644
--- a/src/khoj/processor/conversation/prompts.py
+++ b/src/khoj/processor/conversation/prompts.py
@@ -17,6 +17,11 @@ Current Date: {current_date}
 Question: {query}
 """.strip()
 )
+no_notes_found = PromptTemplate.from_template(
+    """
+    I'm sorry, I couldn't find any relevant notes to respond to your message.
+    """.strip()
+)
 
 system_prompt_message_llamav2 = f"""You are Khoj, a friendly, smart and helpful personal assistant.
 Using your general knowledge and our past conversations as context, answer the following question.
@@ -225,3 +230,17 @@ A:{ "search-type": "notes" }
 Q:When did I go surfing last?
 A:{ "search-type": "notes" }
 Q:"""
+
+
+# System messages to user
+# --
+help_message = PromptTemplate.from_template(
+    """
+**/help**: Show this help message.
+**/notes**: Search only against the information in your knowledge base. This is the default method.
+**/general**: Search general knowledge with the LLM. This will not search against your notes.
+
+You are using the **{model}** model. To change the model, go to your <a href="/config">settings</a> page.
+**version**: {version}
+""".strip()
+)
diff --git a/src/khoj/routers/api.py b/src/khoj/routers/api.py
index 69613177..4c5541b1 100644
--- a/src/khoj/routers/api.py
+++ b/src/khoj/routers/api.py
@@ -18,7 +18,7 @@ from khoj.search_filter.date_filter import DateFilter
 from khoj.search_filter.file_filter import FileFilter
 from khoj.search_filter.word_filter import WordFilter
 from khoj.utils.config import TextSearchModel
-from khoj.utils.helpers import timer
+from khoj.utils.helpers import ConversationCommand, is_none_or_empty, timer, command_descriptions
 from khoj.utils.rawconfig import (
     ContentConfig,
     FullConfig,
@@ -36,7 +36,13 @@ from khoj.utils.state import SearchType
 from khoj.utils import state, constants
 from khoj.utils.yaml import save_config_to_file_updated_state
 from fastapi.responses import StreamingResponse, Response
-from khoj.routers.helpers import perform_chat_checks, generate_chat_response, update_telemetry_state
+from khoj.routers.helpers import (
+    get_conversation_command,
+    perform_chat_checks,
+    generate_chat_response,
+    update_telemetry_state,
+)
+from khoj.processor.conversation.prompts import help_message
 from khoj.processor.conversation.openai.gpt import extract_questions
 from khoj.processor.conversation.gpt4all.chat_model import extract_questions_offline
 from fastapi.requests import Request
@@ -659,6 +665,30 @@ def chat_history(
     return {"status": "ok", "response": meta_log.get("chat", [])}
 
 
+@api.get("/chat/options", response_class=Response)
+async def chat_options(
+    request: Request,
+    client: Optional[str] = None,
+    user_agent: Optional[str] = Header(None),
+    referer: Optional[str] = Header(None),
+    host: Optional[str] = Header(None),
+) -> Response:
+    cmd_options = {}
+    for cmd in ConversationCommand:
+        cmd_options[cmd.value] = command_descriptions[cmd]
+
+    update_telemetry_state(
+        request=request,
+        telemetry_type="api",
+        api="chat_options",
+        client=client,
+        user_agent=user_agent,
+        referer=referer,
+        host=host,
+    )
+    return Response(content=json.dumps(cmd_options), media_type="application/json", status_code=200)
+
+
 @api.get("/chat", response_class=Response)
 async def chat(
     request: Request,
@@ -671,7 +701,15 @@ async def chat(
     host: Optional[str] = Header(None),
 ) -> Response:
     perform_chat_checks()
-    compiled_references, inferred_queries = await extract_references_and_questions(request, q, (n or 5))
+    conversation_command = get_conversation_command(query=q, any_references=True)
+    compiled_references, inferred_queries = await extract_references_and_questions(
+        request, q, (n or 5), conversation_command
+    )
+    conversation_command = get_conversation_command(query=q, any_references=is_none_or_empty(compiled_references))
+    if conversation_command == ConversationCommand.Help:
+        model_type = "offline" if state.processor_config.conversation.enable_offline_chat else "openai"
+        formatted_help = help_message.format(model=model_type, version=state.khoj_version)
+        return StreamingResponse(iter([formatted_help]), media_type="text/event-stream", status_code=200)
 
     # Get the (streamed) chat response from the LLM of choice.
     llm_response = generate_chat_response(
@@ -679,6 +717,7 @@ async def chat(
         meta_log=state.processor_config.conversation.meta_log,
         compiled_references=compiled_references,
         inferred_queries=inferred_queries,
+        conversation_command=conversation_command,
     )
 
     if llm_response is None:
@@ -716,12 +755,12 @@ async def extract_references_and_questions(
     request: Request,
     q: str,
     n: int,
+    conversation_type: ConversationCommand = ConversationCommand.Notes,
 ):
     # Load Conversation History
     meta_log = state.processor_config.conversation.meta_log
 
     # Initialize Variables
-    conversation_type = "general" if q.startswith("@general") else "notes"
     compiled_references: List[Any] = []
     inferred_queries: List[str] = []
 
@@ -731,7 +770,7 @@ async def extract_references_and_questions(
         )
         return compiled_references, inferred_queries
 
-    if conversation_type == "notes":
+    if conversation_type != ConversationCommand.General:
         # Infer search queries from user message
         with timer("Extracting search queries took", logger):
             # If we've reached here, either the user has enabled offline chat or the openai model is enabled.
diff --git a/src/khoj/routers/helpers.py b/src/khoj/routers/helpers.py
index 6d7c511e..63f82a1d 100644
--- a/src/khoj/routers/helpers.py
+++ b/src/khoj/routers/helpers.py
@@ -1,12 +1,12 @@
 import logging
 from datetime import datetime
 from functools import partial
-from typing import List, Optional
+from typing import Iterator, List, Optional, Union
 
 from fastapi import HTTPException, Request
 
 from khoj.utils import state
-from khoj.utils.helpers import timer, log_telemetry
+from khoj.utils.helpers import ConversationCommand, timer, log_telemetry
 from khoj.processor.conversation.openai.gpt import converse
 from khoj.processor.conversation.gpt4all.chat_model import converse_offline
 from khoj.processor.conversation.utils import reciprocal_conversation_to_chatml, message_to_log, ThreadedGenerator
@@ -57,12 +57,27 @@ def update_telemetry_state(
     ]
 
 
+def get_conversation_command(query: str, any_references: bool = False) -> ConversationCommand:
+    if query.startswith("/notes"):
+        return ConversationCommand.Notes
+    elif query.startswith("/general"):
+        return ConversationCommand.General
+    elif query.startswith("/help"):
+        return ConversationCommand.Help
+    # If no relevant notes found for the given query
+    elif not any_references:
+        return ConversationCommand.General
+    else:
+        return ConversationCommand.Notes
+
+
 def generate_chat_response(
     q: str,
     meta_log: dict,
     compiled_references: List[str] = [],
     inferred_queries: List[str] = [],
-) -> ThreadedGenerator:
+    conversation_command: ConversationCommand = ConversationCommand.Notes,
+) -> Union[ThreadedGenerator, Iterator[str]]:
     def _save_to_conversation_log(
         q: str,
         chat_response: str,
@@ -85,12 +100,8 @@ def generate_chat_response(
 
     # Initialize Variables
     user_message_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-    conversation_type = "general" if q.startswith("@general") else "notes"
-
-    # Switch to general conversation type if no relevant notes found for the given query
-    conversation_type = "notes" if compiled_references else "general"
-    logger.debug(f"Conversation Type: {conversation_type}")
     chat_response = None
+    logger.debug(f"Conversation Type: {conversation_command.name}")
 
     try:
         partial_completion = partial(
@@ -110,6 +121,7 @@ def generate_chat_response(
                 loaded_model=loaded_model,
                 conversation_log=meta_log,
                 completion_func=partial_completion,
+                conversation_command=conversation_command,
             )
 
         elif state.processor_config.conversation.openai_model:
@@ -122,6 +134,7 @@ def generate_chat_response(
                 model=chat_model,
                 api_key=api_key,
                 completion_func=partial_completion,
+                conversation_command=conversation_command,
             )
 
     except Exception as e:
diff --git a/src/khoj/utils/helpers.py b/src/khoj/utils/helpers.py
index 72c25bb6..3fca8d8a 100644
--- a/src/khoj/utils/helpers.py
+++ b/src/khoj/utils/helpers.py
@@ -2,6 +2,7 @@
 from __future__ import annotations  # to avoid quoting type hints
 from collections import OrderedDict
 import datetime
+from enum import Enum
 from importlib import import_module
 from importlib.metadata import version
 import logging
@@ -210,3 +211,16 @@ def log_telemetry(
 
     # Log telemetry data to telemetry endpoint
     return request_body
+
+
+class ConversationCommand(str, Enum):
+    General = "general"
+    Notes = "notes"
+    Help = "help"
+
+
+command_descriptions = {
+    ConversationCommand.General: "This command allows you to search talk with the LLM without including context from your knowledge base.",
+    ConversationCommand.Notes: "This command allows you to search talk with the LLM while including context from your knowledge base.",
+    ConversationCommand.Help: "This command displays a help message.",
+}
diff --git a/src/khoj/utils/state.py b/src/khoj/utils/state.py
index 5e6baeae..5ac8a838 100644
--- a/src/khoj/utils/state.py
+++ b/src/khoj/utils/state.py
@@ -30,6 +30,7 @@ SearchType = utils_config.SearchType
 telemetry: List[Dict[str, str]] = []
 previous_query: str = None
 demo: bool = False
+khoj_version: str = None
 
 if torch.cuda.is_available():
     # Use CUDA GPU
diff --git a/tests/conftest.py b/tests/conftest.py
index 871154e7..f093cc84 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -233,22 +233,25 @@ def client(content_config: ContentConfig, search_config: SearchConfig, processor
 
 @pytest.fixture(scope="function")
 def client_offline_chat(
-    content_config: ContentConfig, search_config: SearchConfig, processor_config_offline_chat: ProcessorConfig
+    md_content_config: ContentConfig, search_config: SearchConfig, processor_config_offline_chat: ProcessorConfig
 ):
-    state.config.content_type = content_config
+    # Initialize app state
+    state.config.content_type = md_content_config
     state.config.search_type = search_config
     state.SearchType = configure_search_types(state.config)
 
-    # These lines help us Mock the Search models for these search types
+    # Index Markdown Content for Search
+    filters = [DateFilter(), WordFilter(), FileFilter()]
     state.search_models.text_search = text_search.initialize_model(search_config.asymmetric)
-    state.search_models.image_search = image_search.initialize_model(search_config.image)
-    state.content_index.org = text_search.setup(
-        OrgToJsonl, content_config.org, state.search_models.text_search.bi_encoder, regenerate=False
-    )
-    state.content_index.image = image_search.setup(
-        content_config.image, state.search_models.image_search, regenerate=False
+    state.content_index.markdown = text_search.setup(
+        MarkdownToJsonl,
+        md_content_config.markdown,
+        state.search_models.text_search.bi_encoder,
+        regenerate=False,
+        filters=filters,
     )
 
+    # Initialize Processor from Config
     state.processor_config = configure_processor(processor_config_offline_chat)
 
     configure_routes(app)
diff --git a/tests/test_client.py b/tests/test_client.py
index c60b0ca2..94da2dbf 100644
--- a/tests/test_client.py
+++ b/tests/test_client.py
@@ -209,7 +209,7 @@ def test_notes_search(client, content_config: ContentConfig, search_config: Sear
     assert response.status_code == 200
     # assert actual_data contains "Khoj via Emacs" entry
     search_result = response.json()[0]["entry"]
-    assert "git clone" in search_result
+    assert "git clone https://github.com/khoj-ai/khoj" in search_result
 
 
 # ----------------------------------------------------------------------------------------------------
@@ -267,6 +267,6 @@ def test_notes_search_with_exclude_filter(client, content_config: ContentConfig,
 
     # Assert
     assert response.status_code == 200
-    # assert actual_data does not contains word "Emacs"
+    # assert actual_data does not contains word "clone"
     search_result = response.json()[0]["entry"]
     assert "clone" not in search_result
diff --git a/tests/test_gpt4all_chat_director.py b/tests/test_gpt4all_chat_director.py
index d7386405..111a6a12 100644
--- a/tests/test_gpt4all_chat_director.py
+++ b/tests/test_gpt4all_chat_director.py
@@ -74,7 +74,6 @@ def test_answer_from_chat_history(client_offline_chat):
 
 
 # ----------------------------------------------------------------------------------------------------
-@pytest.mark.xfail(AssertionError, reason="Chat director not capable of answering this question yet")
 @pytest.mark.chatquality
 def test_answer_from_currently_retrieved_content(client_offline_chat):
     # Arrange
@@ -123,7 +122,10 @@ def test_answer_from_chat_history_and_previously_retrieved_content(client_offlin
 
 
 # ----------------------------------------------------------------------------------------------------
-@pytest.mark.xfail(AssertionError, reason="Chat director not capable of answering this question yet")
+@pytest.mark.xfail(
+    AssertionError,
+    reason="Chat director not capable of answering this question yet because it requires extract_questions",
+)
 @pytest.mark.chatquality
 def test_answer_from_chat_history_and_currently_retrieved_content(client_offline_chat):
     # Arrange
diff --git a/tests/test_openai_chat_director.py b/tests/test_openai_chat_director.py
index 15977f71..a28c3d04 100644
--- a/tests/test_openai_chat_director.py
+++ b/tests/test_openai_chat_director.py
@@ -1,9 +1,11 @@
 # Standard Packages
 import os
+import urllib.parse
 
 # External Packages
 import pytest
 from freezegun import freeze_time
+from khoj.processor.conversation import prompts
 
 # Internal Packages
 from khoj.processor.conversation.utils import message_to_log
@@ -168,6 +170,57 @@ def test_no_answer_in_chat_history_or_retrieved_content(chat_client):
     )
 
 
+# ----------------------------------------------------------------------------------------------------
+@pytest.mark.chatquality
+def test_answer_using_general_command(chat_client):
+    # Arrange
+    query = urllib.parse.quote("/general Where was Xi Li born?")
+    message_list = []
+    populate_chat_history(message_list)
+
+    # Act
+    response = chat_client.get(f"/api/chat?q={query}&stream=true")
+    response_message = response.content.decode("utf-8")
+
+    # Assert
+    assert response.status_code == 200
+    assert "Fujiang" not in response_message
+
+
+# ----------------------------------------------------------------------------------------------------
+@pytest.mark.chatquality
+def test_answer_from_retrieved_content_using_notes_command(chat_client):
+    # Arrange
+    query = urllib.parse.quote("/notes Where was Xi Li born?")
+    message_list = []
+    populate_chat_history(message_list)
+
+    # Act
+    response = chat_client.get(f"/api/chat?q={query}&stream=true")
+    response_message = response.content.decode("utf-8")
+
+    # Assert
+    assert response.status_code == 200
+    assert "Fujiang" in response_message
+
+
+# ----------------------------------------------------------------------------------------------------
+@pytest.mark.chatquality
+def test_answer_not_known_using_notes_command(chat_client):
+    # Arrange
+    query = urllib.parse.quote("/notes Where was Testatron born?")
+    message_list = []
+    populate_chat_history(message_list)
+
+    # Act
+    response = chat_client.get(f"/api/chat?q={query}&stream=true")
+    response_message = response.content.decode("utf-8")
+
+    # Assert
+    assert response.status_code == 200
+    assert response_message == prompts.no_notes_found.format()
+
+
 # ----------------------------------------------------------------------------------------------------
 @pytest.mark.xfail(AssertionError, reason="Chat director not capable of answering time aware questions yet")
 @pytest.mark.chatquality