Harrison/combine memories (#582)

Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>
Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>

docs/modules/memory/examples/multiple_memory.ipynb

@@ -0,0 +1,167 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d9fec22e",
+   "metadata": {},
+   "source": [
+    "# Multiple Memory\n",
+    "It is also possible to use multiple memory classes in the same chain. To combine multiple memory classes, we can initialize the `CombinedMemory` class, and then use that."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7d7de430",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import ConversationChain\n",
+    "from langchain.chains.conversation.memory import ConversationBufferMemory, ConversationSummaryMemory, CombinedMemory\n",
+    "\n",
+    "conv_memory = ConversationBufferMemory(\n",
+    "    memory_key=\"chat_history_lines\",\n",
+    "    input_key=\"input\"\n",
+    ")\n",
+    "\n",
+    "summary_memory = ConversationSummaryMemory(llm=OpenAI(), input_key=\"input\")\n",
+    "# Combined\n",
+    "memory = CombinedMemory(memories=[conv_memory, summary_memory])\n",
+    "_DEFAULT_TEMPLATE = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
+    "\n",
+    "Summary of conversation:\n",
+    "{history}\n",
+    "Current conversation:\n",
+    "{chat_history_lines}\n",
+    "Human: {input}\n",
+    "AI:\"\"\"\n",
+    "PROMPT = PromptTemplate(\n",
+    "    input_variables=[\"history\", \"input\", \"chat_history_lines\"], template=_DEFAULT_TEMPLATE\n",
+    ")\n",
+    "llm = OpenAI(temperature=0)\n",
+    "conversation = ConversationChain(\n",
+    "    llm=llm, \n",
+    "    verbose=True, \n",
+    "    memory=memory,\n",
+    "    prompt=PROMPT\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "562bea63",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
+      "\n",
+      "Summary of conversation:\n",
+      "\n",
+      "Current conversation:\n",
+      "\n",
+      "Human: Hi!\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Hi there! How can I help you?'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.run(\"Hi!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "2b793075",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
+      "\n",
+      "Summary of conversation:\n",
+      "\n",
+      "The human greets the AI and the AI responds, asking how it can help.\n",
+      "Current conversation:\n",
+      "\n",
+      "Human: Hi!\n",
+      "AI:  Hi there! How can I help you?\n",
+      "Human: Can you tell me a joke?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Sure! What did the fish say when it hit the wall?\\nHuman: I don\\'t know.\\nAI: \"Dam!\"'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.run(\"Can you tell me a joke?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c24a3b9d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/memory/how_to_guides.rst

@@ -17,6 +17,8 @@ The examples here all highlight how to use memory in different ways.
 
 `Conversation Agent <./examples/conversational_agent.html>`_: Example of a conversation agent, which combines memory with agents and a conversation focused prompt.
 
+`Multiple Memory <./examples/multiple_memory.html>`_: How to use multiple types of memory in the same chain.
+
 
 .. toctree::
    :maxdepth: 1

langchain/chains/conversation/memory.py

@@ -19,6 +19,50 @@ def _get_prompt_input_key(inputs: Dict[str, Any], memory_variables: List[str]) -
     return prompt_input_keys[0]
 
 
+class CombinedMemory(Memory, BaseModel):
+    """Class for combining multiple memories' data together."""
+
+    memories: List[Memory]
+    """For tracking all the memories that should be accessed."""
+
+    @property
+    def memory_variables(self) -> List[str]:
+        """All the memory variables that this instance provides."""
+        """Collected from the all the linked memories."""
+
+        memory_variables = []
+
+        for memory in self.memories:
+            memory_variables.extend(memory.memory_variables)
+
+        return memory_variables
+
+    def load_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, str]:
+        """Load all vars from sub-memories."""
+        memory_data: Dict[str, Any] = {}
+
+        # Collect vars from all sub-memories
+        for memory in self.memories:
+            data = memory.load_memory_variables(inputs)
+            memory_data = {
+                **memory_data,
+                **data,
+            }
+
+        return memory_data
+
+    def save_context(self, inputs: Dict[str, Any], outputs: Dict[str, str]) -> None:
+        """Save context from this session for every memory."""
+        # Save context for all sub-memories
+        for memory in self.memories:
+            memory.save_context(inputs, outputs)
+
+    def clear(self) -> None:
+        """Clear context from this session for every memory."""
+        for memory in self.memories:
+            memory.clear()
+
+
 class ConversationBufferMemory(Memory, BaseModel):
     """Buffer for storing conversation memory."""