Streaming only final output of agent (#2483)

docs/modules/agents/streaming_stdout_final_only.ipynb

@@ -0,0 +1,154 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "23234b50-e6c6-4c87-9f97-259c15f36894",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Only streaming final agent output"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "29dd6333-307c-43df-b848-65001c01733b",
+   "metadata": {},
+   "source": [
+    "If you only want the final output of an agent to be streamed, you can use the callback ``FinalStreamingStdOutCallbackHandler``.\n",
+    "For this, the underlying LLM has to support streaming as well."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e4592215-6604-47e2-89ff-5db3af6d1e40",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.agents import load_tools\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.agents import AgentType\n",
+    "from langchain.callbacks.streaming_stdout_final_only import FinalStreamingStdOutCallbackHandler\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19a813f7",
+   "metadata": {},
+   "source": [
+    "Let's create the underlying LLM with ``streaming = True`` and pass a new instance of ``FinalStreamingStdOutCallbackHandler``."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7fe81ef4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(streaming=True, callbacks=[FinalStreamingStdOutCallbackHandler()], temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ff45b85d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Konrad Adenauer became Chancellor of Germany in 1949, 74 years ago in 2023."
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Konrad Adenauer became Chancellor of Germany in 1949, 74 years ago in 2023.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = load_tools([\"wikipedia\", \"llm-math\"], llm=llm)\n",
+    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False)\n",
+    "agent.run(\"It's 2023 now. How many years ago did Konrad Adenauer become Chancellor of Germany.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53a743b8",
+   "metadata": {},
+   "source": [
+    "### Handling custom answer prefixes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "23602c62",
+   "metadata": {},
+   "source": [
+    "By default, we assume that the token sequence ``\"\\nFinal\", \" Answer\", \":\"`` indicates that the agent has reached an answers. We can, however, also pass a custom sequence to use as answer prefix."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5662a638",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(\n",
+    "    streaming=True,\n",
+    "    callbacks=[FinalStreamingStdOutCallbackHandler(answer_prefix_tokens=[\"\\nThe\", \" answer\", \":\"])],\n",
+    "    temperature=0\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b1a96cc0",
+   "metadata": {},
+   "source": [
+    "Be aware you likely need to include whitespaces and new line characters in your token. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9278b522",
+   "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

langchain/callbacks/streaming_stdout_final_only.py

@@ -0,0 +1,49 @@
+"""Callback Handler streams to stdout on new llm token."""
+import sys
+from typing import Any, Dict, List, Optional
+
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
+DEFAULT_ANSWER_PREFIX_TOKENS = ["\nFinal", " Answer", ":"]
+
+
+class FinalStreamingStdOutCallbackHandler(StreamingStdOutCallbackHandler):
+    """Callback handler for streaming in agents.
+    Only works with agents using LLMs that support streaming.
+
+    Only the final output of the agent will be streamed.
+    """
+
+    def __init__(self, answer_prefix_tokens: Optional[List[str]] = None) -> None:
+        super().__init__()
+        if answer_prefix_tokens is None:
+            answer_prefix_tokens = DEFAULT_ANSWER_PREFIX_TOKENS
+        self.answer_prefix_tokens = answer_prefix_tokens
+        self.last_tokens = [""] * len(answer_prefix_tokens)
+        self.answer_reached = False
+
+    def on_llm_start(
+        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
+    ) -> None:
+        """Run when LLM starts running."""
+        self.answer_reached = False
+
+    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
+        """Run on new LLM token. Only available when streaming is enabled."""
+
+        # Remember the last n tokens, where n = len(answer_prefix_tokens)
+        self.last_tokens.append(token)
+        if len(self.last_tokens) > len(self.answer_prefix_tokens):
+            self.last_tokens.pop(0)
+
+        # Check if the last n tokens match the answer_prefix_tokens list ...
+        if self.last_tokens == self.answer_prefix_tokens:
+            self.answer_reached = True
+            # Do not print the last token in answer_prefix_tokens,
+            # as it's not part of the answer yet
+            return
+
+        # ... if yes, then print tokens from now on
+        if self.answer_reached:
+            sys.stdout.write(token)
+            sys.stdout.flush()