fix headers (#2039)

docs/modules/memory/types/buffer.ipynb

@@ -5,7 +5,7 @@
    "id": "46196aa3",
    "metadata": {},
    "source": [
-    "## ConversationBufferMemory\n",
+    "# ConversationBufferMemory\n",
     "\n",
     "This notebook shows how to use `ConversationBufferMemory`. This memory allows for storing of messages and then extracts the messages in a variable.\n",
     "\n",

docs/modules/memory/types/buffer_window.ipynb

@@ -5,7 +5,7 @@
    "id": "a20c4e38",
    "metadata": {},
    "source": [
-    "## ConversationBufferWindowMemory\n",
+    "# ConversationBufferWindowMemory\n",
     "\n",
     "`ConversationBufferWindowMemory` keeps a list of the interactions of the conversation over time. It only uses the last K interactions. This can be useful for keeping a sliding window of the most recent interactions, so the buffer does not get too large\n",
     "\n",

docs/modules/memory/types/kg.ipynb

@@ -5,7 +5,7 @@
    "id": "44c9933a",
    "metadata": {},
    "source": [
-    "## Conversation Knowledge Graph Memory\n",
+    "# Conversation Knowledge Graph Memory\n",
     "\n",
     "This type of memory uses a knowledge graph to recreate memory.\n",
     "\n",

docs/modules/memory/types/summary.ipynb

@@ -5,7 +5,7 @@
    "id": "1674bfd6",
    "metadata": {},
    "source": [
-    "## ConversationSummaryMemory\n",
+    "# ConversationSummaryMemory\n",
     "Now let's take a look at using a slightly more complex type of memory - `ConversationSummaryMemory`. This type of memory creates a summary of the conversation over time. This can be useful for condensing information from the conversation over time.\n",
     "\n",
     "Let's first explore the basic functionality of this type of memory."

docs/modules/memory/types/summary_buffer.ipynb

@@ -5,7 +5,7 @@
    "id": "ff4be5f3",
    "metadata": {},
    "source": [
-    "## ConversationSummaryBufferMemory\n",
+    "# ConversationSummaryBufferMemory\n",
     "\n",
     "`ConversationSummaryBufferMemory` combines the last two ideas. It keeps a buffer of recent interactions in memory, but rather than just completely flushing old interactions it compiles them into a summary and uses both. Unlike the previous implementation though, it uses token length rather than number of interactions to determine when to flush interactions.\n",
     "\n",

docs/modules/memory/types/token_buffer.ipynb

@@ -5,7 +5,7 @@
    "id": "ff4be5f3",
    "metadata": {},
    "source": [
-    "## ConversationTokenBufferMemory\n",
+    "# ConversationTokenBufferMemory\n",
     "\n",
     "`ConversationTokenBufferMemory` keeps a buffer of recent interactions in memory, and uses token length rather than number of interactions to determine when to flush interactions.\n",
     "\n",