Merge branch 'langchain-ai:master' into master

.github/actions/poetry_setup/action.yml

@@ -26,7 +26,7 @@ inputs:
 runs:
   using: composite
   steps:
-    - uses: actions/setup-python@v4
+    - uses: actions/setup-python@v5
       name: Setup python ${{ inputs.python-version }}
       with:
         python-version: ${{ inputs.python-version }}

.github/workflows/check_diffs.yml

@@ -5,11 +5,6 @@ on:
   push:
     branches: [master]
   pull_request:
-    paths:
-      - ".github/actions/**"
-      - ".github/tools/**"
-      - ".github/workflows/**"
-      - "libs/**"
 
 # If another push to the same PR or branch happens while this workflow is still running,
 # cancel the earlier run in favor of the next run.
@@ -26,7 +21,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: '3.10'
       - id: files

.github/workflows/scheduled_test.yml

@@ -36,7 +36,7 @@ jobs:
 
       - name: 'Authenticate to Google Cloud'
         id: 'auth'
-        uses: 'google-github-actions/auth@v1'
+        uses: google-github-actions/auth@v2
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 

.readthedocs.yaml

@@ -10,7 +10,7 @@ build:
   tools:
     python: "3.11"
   commands:
-      - python -mvirtualenv $READTHEDOCS_VIRTUALENV_PATH
+      - python -m virtualenv $READTHEDOCS_VIRTUALENV_PATH
       - python -m pip install --upgrade --no-cache-dir pip setuptools
       - python -m pip install --upgrade --no-cache-dir sphinx readthedocs-sphinx-ext
       - python -m pip install ./libs/partners/*

cookbook/LLaMA2_sql_chat.ipynb

@@ -125,7 +125,7 @@
    "id": "654b3577-baa2-4e12-a393-f40e5db49ac7",
    "metadata": {},
    "source": [
-    "## Query a SQL DB \n",
+    "## Query a SQL Database \n",
     "\n",
     "Follow the runnables workflow [here](https://python.langchain.com/docs/expression_language/cookbook/sql_db)."
    ]
@@ -151,6 +151,7 @@
     "# Prompt\n",
     "from langchain.prompts import ChatPromptTemplate\n",
     "\n",
+    "# Update the template based on the type of SQL Database like MySQL, Microsoft SQL Server and so on\n",
     "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
     "{schema}\n",
     "\n",

cookbook/Multi_modal_RAG.ipynb

@@ -341,7 +341,7 @@
     "Add raw docs and doc summaries to [Multi Vector Retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector#summary): \n",
     "\n",
     "* Store the raw texts, tables, and images in the `docstore`.\n",
-    "* Store the texts, table summaries, and image summaries in the `vectorstore` for semantic retrieval."
+    "* Store the texts, table summaries, and image summaries in the `vectorstore` for efficient semantic retrieval."
    ]
   },
   {

docs/docs/modules/agents/how_to/agent_vectorstore.ipynb → cookbook/agent_vectorstore.ipynb

@@ -13,7 +13,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "9b22020a",
    "metadata": {},
@@ -146,7 +145,6 @@
    "source": []
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "c0a6c031",
    "metadata": {},
@@ -280,7 +278,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "787a9b5e",
    "metadata": {},
@@ -289,7 +286,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "9161ba91",
    "metadata": {},
@@ -411,7 +407,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "49a0cbbe",
    "metadata": {},
@@ -525,7 +520,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/docs/modules/agents/how_to/custom_agent_with_tool_retrieval.ipynb → cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -7,8 +7,6 @@
    "source": [
     "# Custom agent with tool retrieval\n",
     "\n",
-    "This notebook builds off of [this notebook](/docs/modules/agents/how_to/custom_llm_agent) and assumes familiarity with how agents work.\n",
-    "\n",
     "The novel idea introduced in this notebook is the idea of using retrieval to select the set of tools to use to answer an agent query. This is useful when you have many many tools to select from. You cannot put the description of all the tools in the prompt (because of context length issues) so instead you dynamically select the N tools you do want to consider using at run time.\n",
     "\n",
     "In this notebook we will create a somewhat contrived example. We will have one legitimate tool (search) and then 99 fake tools which are just nonsense. We will then add a step in the prompt template that takes the user input and retrieves tool relevant to the query."
@@ -489,7 +487,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.1"
   },
   "vscode": {
    "interpreter": {

docs/docs/expression_language/cookbook/agent.ipynb

@@ -12,18 +12,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 8,
    "id": "af4381de",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import AgentExecutor, XMLAgent, tool\n",
+    "from langchain import hub\n",
+    "from langchain.agents import AgentExecutor, tool\n",
+    "from langchain.agents.output_parsers import XMLAgentOutputParser\n",
     "from langchain.chat_models import ChatAnthropic"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "24cc8134",
    "metadata": {},
    "outputs": [],
@@ -33,7 +35,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "67c0b0e4",
    "metadata": {},
    "outputs": [],
@@ -46,7 +48,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "7203b101",
    "metadata": {},
    "outputs": [],
@@ -56,18 +58,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "b68e756d",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Get prompt to use\n",
-    "prompt = XMLAgent.get_default_prompt()"
+    "# Get the prompt to use - you can modify this!\n",
+    "prompt = hub.pull(\"hwchase17/xml-agent-convo\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "61ab3e9a",
    "metadata": {},
    "outputs": [],
@@ -107,27 +109,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 12,
    "id": "e92f1d6f",
    "metadata": {},
    "outputs": [],
    "source": [
     "agent = (\n",
     "    {\n",
-    "        \"question\": lambda x: x[\"question\"],\n",
-    "        \"intermediate_steps\": lambda x: convert_intermediate_steps(\n",
+    "        \"input\": lambda x: x[\"input\"],\n",
+    "        \"agent_scratchpad\": lambda x: convert_intermediate_steps(\n",
     "            x[\"intermediate_steps\"]\n",
     "        ),\n",
     "    }\n",
     "    | prompt.partial(tools=convert_tools(tool_list))\n",
     "    | model.bind(stop=[\"</tool_input>\", \"</final_answer>\"])\n",
-    "    | XMLAgent.get_default_output_parser()\n",
+    "    | XMLAgentOutputParser()\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 13,
    "id": "6ce6ec7a",
    "metadata": {},
    "outputs": [],
@@ -137,7 +139,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 14,
    "id": "fb5cb2e3",
    "metadata": {},
    "outputs": [
@@ -148,28 +150,26 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m <tool>search</tool>\n",
-      "<tool_input>weather in new york\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m\n",
-      "\n",
-      "<final_answer>The weather in New York is 32 degrees\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m <tool>search</tool><tool_input>weather in New York\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m <tool>search</tool>\n",
+      "<tool_input>weather in New York\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m <final_answer>The weather in New York is 32 degrees\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "{'question': 'whats the weather in New york?',\n",
+       "{'input': 'whats the weather in New york?',\n",
        " 'output': 'The weather in New York is 32 degrees'}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent_executor.invoke({\"question\": \"whats the weather in New york?\"})"
+    "agent_executor.invoke({\"input\": \"whats the weather in New york?\"})"
    ]
   },
   {

docs/docs/expression_language/how_to/passthrough.ipynb

@@ -66,7 +66,7 @@
     "\n",
     "In the second line, we used `RunnablePastshrough.assign` with a lambda that multiplies the numerical value by 3. In this cased, `extra` was set with `{'num': 1, 'mult': 3}` which is the original value with the `mult` key added. \n",
     "\n",
-    "Finally, we also set a third key in the map with `modified` which uses a labmda to set a single value adding 1 to the num, which resulted in `modified` key with the value of `2`."
+    "Finally, we also set a third key in the map with `modified` which uses a lambda to set a single value adding 1 to the num, which resulted in `modified` key with the value of `2`."
    ]
   },
   {