Merge branch 'main' into wfh/recurse

README.md

@@ -511,6 +511,11 @@ It can often be tough to evaluation chat bots in multi-turn situations. One way
 
 - [WebVoyager](https://github.com/langchain-ai/langgraph/blob/main/examples/web-navigation/web_voyager.ipynb): vision-enabled web browsing agent that uses [Set-of-marks](https://som-gpt4v.github.io/) prompting to navigate a web browser and execute tasks
 
+### [Chain-of-Table](https://github.com/CYQIQ/MultiCoT)
+
+[Chain of Table](https://arxiv.org/abs/2401.04398) is a framework that elicits SOTA performance when answering questions over tabular data. [This implementation](https://github.com/CYQIQ/MultiCoT) by Github user [CYQIQ](https://github.com/CYQIQ) uses LangGraph to control the flow.
+
+
 ## Documentation
 
 There are only a few new APIs to use.

examples/code_assistant/langgraph_code_assistant.ipynb

@@ -29,7 +29,7 @@
     "\n",
     "Recent works, such as AlphaCodium, have shown that code generation can be [substantially improved by using a \"flow\" paradigm](https://x.com/karpathy/status/1748043513156272416?s=20).\n",
     "\n",
-    "Rather than naive `prompt:answer` paradigm, a `flow` paradigm constructs an answer to a coding question iteratively.\n",
+    "Rather than a naive `prompt:answer` paradigm, a `flow` paradigm constructs an answer to a coding question iteratively.\n",
     "\n",
     "[AlphaCodium](https://github.com/Codium-ai/AlphaCodium) iteravely tests and improves an answer on public and AI-generated tests for a particular question. \n",
     "\n",
@@ -39,7 +39,7 @@
     "\n",
     "## LangGraph self-corrective code assistant\n",
     "\n",
-    "We wanted to test these the general idea of iterative code generation in LangGraph, making a few simplifications relative to the AlphaCodium work:\n",
+    "We wanted to test the general idea of iterative code generation in LangGraph, making a few simplifications relative to the AlphaCodium work:\n",
     "\n",
     "1. We start with a set of documentation specified by a user\n",
     "2. We use a long context LLM to ingest it, and answer a question based upon it \n",

examples/rag/langgraph_agentic_rag.ipynb

@@ -267,7 +267,7 @@
     "\n",
     "    else:\n",
     "        print(\"---DECISION: DOCS NOT RELEVANT---\")\n",
-    "        print(score.binary_score)\n",
+    "        print(grade)\n",
     "        return \"no\"\n",
     "\n",
     "\n",
@@ -338,7 +338,7 @@
     "    messages = state[\"messages\"]\n",
     "    question = messages[0].content\n",
     "\n",
-    "    msg = HumanMessage(\n",
+    "    msg = [HumanMessage(\n",
     "        content=f\"\"\" \\n \n",
     "    Look at the input and try to reason about the underlying semantic intent / meaning. \\n \n",
     "    Here is the initial question:\n",
@@ -346,7 +346,7 @@
     "    {question} \n",
     "    \\n ------- \\n\n",
     "    Formulate an improved question: \"\"\",\n",
-    "    )\n",
+    "    )]\n",
     "\n",
     "    # Grader\n",
     "    model = ChatOpenAI(temperature=0, model=\"gpt-4-0125-preview\", streaming=True)\n",

examples/rewoo/rewoo.ipynb

@@ -342,6 +342,7 @@
     "        _results = state[\"results\"] or {}\n",
     "        for k, v in _results.items():\n",
     "            tool_input = tool_input.replace(k, v)\n",
+    "            step_name = step_name.replace(k, v)\n",
     "        plan += f\"Plan: {_plan}\\n{step_name} = {tool}[{tool_input}]\"\n",
     "    prompt = solve_prompt.format(plan=plan, task=state[\"task\"])\n",
     "    result = model.invoke(prompt)\n",