docs: ReAct reference (#22830)

The `ReAct` is used all across LangChain but it is not referenced properly. Added references to the original paper.
langchain-ai · Jun 20, 2024 · b8d3050 · b8d3050
1 parent aae831f
commit b8d3050
Show file tree

Hide file tree

Showing 6 changed files with 70 additions and 12 deletions.
diff --git a/docs/docs/additional_resources/arxiv_references.mdx b/docs/docs/additional_resources/arxiv_references.mdx
diff --git a/docs/docs/integrations/chat/huggingface.ipynb b/docs/docs/integrations/chat/huggingface.ipynb
@@ -315,7 +315,11 @@
    "source": [
     "## 4. Take it for a spin as an agent!\n",
     "\n",
-    "Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. The example below is taken from [here](https://python.langchain.com/v0.1/docs/modules/agents/agent_types/react/#using-chat-models).\n",
+    "Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. \n",
+    "\n",
+    "The agent is based on the paper [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629)\n",
+    "\n",
+    "The example below is taken from [here](https://python.langchain.com/v0.1/docs/modules/agents/agent_types/react/#using-chat-models).\n",
     "\n",
     "> Note: To run this section, you'll need to have a [SerpAPI Token](https://serpapi.com/) saved as an environment variable: `SERPAPI_API_KEY`"
    ]

diff --git a/docs/docs/integrations/providers/cohere.mdx b/docs/docs/integrations/providers/cohere.mdx
@@ -48,6 +48,9 @@ print(llm.invoke("Come up with a pet name"))
 Usage of the Cohere (legacy) [LLM model](/docs/integrations/llms/cohere) 
 ### ReAct Agent
 
+The agent is based on the paper
+[ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629).
+
 ```python
 from langchain_community.tools.tavily_search import TavilySearchResults
 from langchain_cohere import ChatCohere, create_cohere_react_agent

diff --git a/docs/docs/integrations/tools/ionic_shopping.ipynb b/docs/docs/integrations/tools/ionic_shopping.ipynb
@@ -82,6 +82,7 @@
     "\n",
     "# Based on ReAct Agent\n",
     "# https://python.langchain.com/docs/modules/agents/agent_types/react\n",
+    "# See the paper \"ReAct: Synergizing Reasoning and Acting in Language Models\" (https://arxiv.org/abs/2210.03629)\n",
     "# Please reach out to [email protected] for help with add'l agent types.\n",
     "\n",
     "open_ai_key = \"YOUR KEY HERE\"\n",
@@ -168,14 +169,23 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3",
+   "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",
-   "version": "3.11.4"
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 4
 }
diff --git a/libs/langchain/langchain/agents/react/agent.py b/libs/langchain/langchain/agents/react/agent.py
@@ -24,6 +24,9 @@ def create_react_agent(
 ) -> Runnable:
     """Create an agent that uses ReAct prompting.
 
+    Based on paper "ReAct: Synergizing Reasoning and Acting in Language Models"
+    (https://arxiv.org/abs/2210.03629)
+
     Args:
         llm: LLM to use as the agent.
         tools: Tools this agent has access to.

diff --git a/libs/langchain/langchain/evaluation/agents/trajectory_eval_chain.py b/libs/langchain/langchain/evaluation/agents/trajectory_eval_chain.py
@@ -103,6 +103,8 @@ class TrajectoryEvalChain(AgentTrajectoryEvaluator, LLMEvalChain):
 
     This chain is used to evaluate ReAct style agents by reasoning about
     the sequence of actions taken and their outcomes.
+    Based on the paper "ReAct: Synergizing Reasoning and Acting in Language Models"
+    (https://arxiv.org/abs/2210.03629)
 
     Example: