docs: Tutorials up to date (#1734)

* edits

* add js code to web voyager

docs/docs/tutorials/rag/langgraph_adaptive_rag.ipynb

@@ -254,7 +254,7 @@
     "\n",
     "retrieval_grader = grade_prompt | structured_llm_grader\n",
     "question = \"agent memory\"\n",
-    "docs = retriever.get_relevant_documents(question)\n",
+    "docs = retriever.invoke(question)\n",
     "doc_txt = docs[1].page_content\n",
     "print(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"
    ]

docs/docs/tutorials/rag/langgraph_adaptive_rag_local.ipynb

@@ -110,7 +110,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "af8379bd-7eae-4ba6-b632-12e89eab9920",
    "metadata": {},
    "outputs": [],
@@ -132,7 +132,16 @@
    "execution_count": 3,
    "id": "f9ff6b99-080d-4827-b2cb-f775543d76f5",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Downloading: 100%|██████████| 274M/274M [00:43<00:00, 6.38MiB/s] \n",
+      "Verifying: 100%|██████████| 274M/274M [00:00<00:00, 618MiB/s] \n"
+     ]
+    }
+   ],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
@@ -178,6 +187,14 @@
    "id": "7045e064-e666-4aea-9111-6e9d2007f27e",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/td/vzm913rx77x21csd90g63_7c0000gn/T/ipykernel_7200/1754575056.py:22: LangChainDeprecationWarning: The method `BaseRetriever.get_relevant_documents` was deprecated in langchain-core 0.1.46 and will be removed in 1.0. Use invoke instead.\n",
+      "  docs = retriever.get_relevant_documents(question)\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -215,7 +232,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "id": "813cdcef-8b75-4214-a2ed-b89077b3d287",
    "metadata": {},
    "outputs": [
@@ -257,15 +274,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 6,
    "id": "aeb8b373-0289-4dec-bd4b-8b2701200301",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/isaachershenson/.pyenv/versions/3.11.9/lib/python3.11/site-packages/langsmith/client.py:5301: LangChainBetaWarning: The function `loads` is in beta. It is actively being worked on, so the API may change.\n",
+      "  prompt = loads(json.dumps(prompt_object.manifest))\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " In an LLM-powered autonomous agent system, the Large Language Model (LLM) functions as the agent's brain. The agent has key components including memory, planning, and reflection mechanisms. The memory component is a long-term memory module that records a comprehensive list of agents’ experience in natural language. It includes a memory stream, which is an external database for storing past experiences. The reflection mechanism synthesizes memories into higher-level inferences over time and guides the agent's future behavior.\n"
+      "1. In an LLM-powered autonomous agent system, the memory component is divided into short-term and long-term memories. Short-term memory utilizes in-context learning, while long-term memory provides the capability to retain and recall information over extended periods using an external vector store.\n",
+      "2. The long-term memory module, also known as the memory stream, records a comprehensive list of agents' experiences in natural language.\n",
+      "3. The agent learns to call external APIs for extra information that is missing from the model weights, including current information, code execution capability, access to proprietary information sources and more.\n"
      ]
     }
    ],
@@ -299,7 +326,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "id": "38345cff-e2d0-436e-aa09-599522a61eed",
    "metadata": {},
    "outputs": [
@@ -309,7 +336,7 @@
        "{'score': 'yes'}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -339,7 +366,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "id": "9771caa1-5542-47c3-8354-aeeafcf51964",
    "metadata": {},
    "outputs": [
@@ -349,7 +376,7 @@
        "{'score': 'yes'}"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -379,17 +406,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 9,
    "id": "830ba5f7-9c8d-4c01-83b1-e4d51d40d48f",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "' What is agent memory and how can it be effectively utilized in vector database retrieval?'"
+       "\" What is the function of an agent's memory in a given context?\""
       ]
      },
-     "execution_count": 11,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -422,7 +449,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "id": "6c3c1c70-ff84-41e8-bf72-738ed52f2dde",
    "metadata": {},
    "outputs": [],
@@ -448,7 +475,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "id": "6e09087e-b2a9-437a-abee-129e426df799",
    "metadata": {},
    "outputs": [],
@@ -475,7 +502,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "id": "7c5fa507-77ae-426a-a65f-f518b9525bd0",
    "metadata": {},
    "outputs": [],
@@ -700,7 +727,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 13,
    "id": "450eb313-ca75-4a43-b57e-7034bd3f40bf",
    "metadata": {},
    "outputs": [],
@@ -752,7 +779,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 14,
    "id": "b095c1db-8bd1-4a34-937c-1a9b74ae74ff",
    "metadata": {},
    "outputs": [
@@ -762,11 +789,35 @@
      "text": [
       "---ROUTE QUESTION---\n",
       "What is the AlphaCodium paper about?\n",
-      "{'datasource': 'web_search'}\n",
-      "web_search\n",
-      "---ROUTE QUESTION TO WEB SEARCH---\n",
-      "---WEB SEARCH---\n",
-      "\"Node 'web_search':\"\n",
+      "{'datasource': 'vectorstore'}\n",
+      "vectorstore\n",
+      "---ROUTE QUESTION TO RAG---\n",
+      "---RETRIEVE---\n",
+      "\"Node 'retrieve':\"\n",
+      "'\\n---\\n'\n",
+      "---CHECK DOCUMENT RELEVANCE TO QUESTION---\n",
+      "---GRADE: DOCUMENT NOT RELEVANT---\n",
+      "---GRADE: DOCUMENT NOT RELEVANT---\n",
+      "---GRADE: DOCUMENT NOT RELEVANT---\n",
+      "---GRADE: DOCUMENT NOT RELEVANT---\n",
+      "---ASSESS GRADED DOCUMENTS---\n",
+      "---DECISION: ALL DOCUMENTS ARE NOT RELEVANT TO QUESTION, TRANSFORM QUERY---\n",
+      "\"Node 'grade_documents':\"\n",
+      "'\\n---\\n'\n",
+      "---TRANSFORM QUERY---\n",
+      "\"Node 'transform_query':\"\n",
+      "'\\n---\\n'\n",
+      "---RETRIEVE---\n",
+      "\"Node 'retrieve':\"\n",
+      "'\\n---\\n'\n",
+      "---CHECK DOCUMENT RELEVANCE TO QUESTION---\n",
+      "---GRADE: DOCUMENT NOT RELEVANT---\n",
+      "---GRADE: DOCUMENT RELEVANT---\n",
+      "---GRADE: DOCUMENT RELEVANT---\n",
+      "---GRADE: DOCUMENT NOT RELEVANT---\n",
+      "---ASSESS GRADED DOCUMENTS---\n",
+      "---DECISION: GENERATE---\n",
+      "\"Node 'grade_documents':\"\n",
       "'\\n---\\n'\n",
       "---GENERATE---\n",
       "---CHECK HALLUCINATIONS---\n",
@@ -775,14 +826,15 @@
       "---DECISION: GENERATION ADDRESSES QUESTION---\n",
       "\"Node 'generate':\"\n",
       "'\\n---\\n'\n",
-      "(' The AlphaCodium paper introduces a new approach for code generation by '\n",
-      " 'Large Language Models (LLMs). It presents AlphaCodium, an iterative process '\n",
-      " 'that involves generating additional data to aid the flow, and testing it on '\n",
-      " 'the CodeContests dataset. The results show that AlphaCodium outperforms '\n",
-      " \"DeepMind's AlphaCode and AlphaCode2 without fine-tuning a model. The \"\n",
-      " 'approach includes a pre-processing phase for problem reasoning in natural '\n",
-      " 'language and an iterative code generation phase with runs and fixes against '\n",
-      " 'tests.')\n"
+      "(' The \"AlphaCodium\" research paper appears to focus on the development and '\n",
+      " 'comparison of an autonomous agent system powered by a large language model '\n",
+      " '(LLM). The system is compared with several baselines, including ED, source '\n",
+      " 'policy, and RL^2. The LLM-powered agent demonstrates impressive performance '\n",
+      " 'in in-context reinforcement learning, getting close to the performance of '\n",
+      " 'RL^2 despite only using offline RL and learning much faster than other '\n",
+      " 'baselines. Additionally, the paper discusses the use of adversarial attacks '\n",
+      " 'on LLMs as a potential threat to their safe behavior in real-world '\n",
+      " 'applications.')\n"
      ]
     }
    ],
@@ -830,7 +882,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/tutorials/rag/langgraph_crag.ipynb

@@ -188,7 +188,7 @@
     "\n",
     "retrieval_grader = grade_prompt | structured_llm_grader\n",
     "question = \"agent memory\"\n",
-    "docs = retriever.get_relevant_documents(question)\n",
+    "docs = retriever.invoke(question)\n",
     "doc_txt = docs[1].page_content\n",
     "print(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"
    ]

docs/docs/tutorials/rag/langgraph_self_rag.ipynb

@@ -109,7 +109,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "565a6d44-2c9f-4fff-b1ec-eea05df9350d",
    "metadata": {},
    "outputs": [],
@@ -152,23 +152,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "1fafad21-60cc-483e-92a3-6a7edb1838e3",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/rlm/miniforge3/envs/llama2/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:119: LangChainDeprecationWarning: The method `BaseRetriever.get_relevant_documents` was deprecated in langchain-core 0.1.46 and will be removed in 0.3.0. Use invoke instead.\n",
-      "  warn_deprecated(\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "binary_score='yes'\n"
+      "binary_score='no'\n"
      ]
     }
    ],
@@ -209,14 +201,14 @@
     "\n",
     "retrieval_grader = grade_prompt | structured_llm_grader\n",
     "question = \"agent memory\"\n",
-    "docs = retriever.get_relevant_documents(question)\n",
+    "docs = retriever.invoke(question)\n",
     "doc_txt = docs[1].page_content\n",
     "print(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 7,
    "id": "dcd77cc1-4587-40ec-b633-5364eab9e1ec",
    "metadata": {},
    "outputs": [
@@ -224,7 +216,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The design of generative agents combines LLM with memory, planning, and reflection mechanisms to enable agents to behave conditioned on past experience and interact with other agents. Long-term memory provides the agent with the capability to retain and recall infinite information over extended periods. Short-term memory is utilized for in-context learning.\n"
+      "The design of generative agents combines LLM with memory, planning, and reflection mechanisms to enable agents to behave conditioned on past experience. Memory stream is a long-term memory module that records a comprehensive list of agents' experience in natural language. LLM functions as the agent's brain in an autonomous agent system.\n"
      ]
     }
    ],
@@ -256,7 +248,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 8,
    "id": "e78931ec-940c-46ad-a0b2-f43f953f1fd7",
    "metadata": {},
    "outputs": [
@@ -266,7 +258,7 @@
        "GradeHallucinations(binary_score='yes')"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -304,7 +296,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "id": "bd62276f-bf26-40d0-8cff-e07b10e00321",
    "metadata": {},
    "outputs": [
@@ -314,7 +306,7 @@
        "GradeAnswer(binary_score='yes')"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -352,7 +344,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 10,
    "id": "c6f4c70e-1660-4149-82c0-837f19fc9fb5",
    "metadata": {},
    "outputs": [
@@ -362,7 +354,7 @@
        "\"What is the role of memory in an agent's functioning?\""
       ]
      },
-     "execution_count": 6,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/docs/tutorials/rag/langgraph_self_rag_local.ipynb

@@ -223,7 +223,7 @@
     "\n",
     "retrieval_grader = prompt | llm | JsonOutputParser()\n",
     "question = \"agent memory\"\n",
-    "docs = retriever.get_relevant_documents(question)\n",
+    "docs = retriever.invoke(question)\n",
     "doc_txt = docs[1].page_content\n",
     "print(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"
    ]