diff --git a/examples/rag/langgraph_adaptive_rag_cohere.ipynb b/examples/rag/langgraph_adaptive_rag_cohere.ipynb index 5402c9c25..4d0ee4394 100644 --- a/examples/rag/langgraph_adaptive_rag_cohere.ipynb +++ b/examples/rag/langgraph_adaptive_rag_cohere.ipynb @@ -165,7 +165,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 2, "id": "bYK-e0diGdPf", "metadata": { "colab": { @@ -179,8 +179,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "[{'id': '3370f44e-01e3-4dc5-a439-543235380ec4', 'function': {'name': 'web_search', 'arguments': '{\"query\": \"who will the bears pick in the NFL draft\"}'}, 'type': 'function'}]\n", - "[{'id': '08933491-a419-4b65-8a48-3ff1e55d8eba', 'function': {'name': 'vectorstore', 'arguments': '{\"query\": \"types of agent memory\"}'}, 'type': 'function'}]\n", + "[{'id': 'f811e3b9-052e-49db-a234-5fc3efbcc5ba', 'function': {'name': 'web_search', 'arguments': '{\"query\": \"NFL draft bears first pick\"}'}, 'type': 'function'}]\n", + "[{'id': '4bc53113-8f32-4d6d-ac9b-c07ef9aae9fd', 'function': {'name': 'vectorstore', 'arguments': '{\"query\": \"types of agent memory\"}'}, 'type': 'function'}]\n", "False\n" ] } @@ -243,14 +243,6 @@ "outputId": "57a5c27b-044b-4df5-f55d-7bf23d3976d1" }, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/Users/rlm/miniforge3/envs/llama2/lib/python3.11/site-packages/langchain_core/_api/beta_decorator.py:87: LangChainBetaWarning: The function `with_structured_output` is in beta. It is actively being worked on, so the API may change.\n", - " warn_beta(\n" - ] - }, { "name": "stdout", "output_type": "stream", @@ -317,7 +309,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "There are three types of agent memory: sensory, short-term and long-term. Sensory memory lasts for a few seconds and deals with sensory information. Short-term memory is finite and restricted by the length of an agent's context window. Long-term memory is infinite and can last for extended periods.\n" + "There are three types of agent memory: sensory memory, short-term memory, and long-term memory.\n" ] } ], @@ -354,19 +346,9 @@ "print(generation)" ] }, - { - "cell_type": "markdown", - "id": "Ezioqk0tGZ-J", - "metadata": { - "id": "Ezioqk0tGZ-J" - }, - "source": [ - "Hallucination Grader" - ] - }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 6, "id": "bc000a7d-84b6-4eb2-88ad-65cc62a44431", "metadata": {}, "outputs": [ @@ -374,7 +356,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Hello! I'm doing well, thank you for asking. As an AI chatbot, I respond to questions and requests while adhering to ethical guidelines and remain polite and helpful. How can I assist you today?\n" + "I don't have feelings as an AI chatbot, but I'm here to assist you with any queries or concerns you may have. How can I help you today?\n" ] } ], @@ -413,7 +395,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 7, "id": "y0msuR2DHQkY", "metadata": { "colab": { @@ -429,7 +411,7 @@ "GradeHallucinations(binary_score='yes')" ] }, - "execution_count": 6, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -465,7 +447,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 8, "id": "f0c08d14-77a0-4eed-b882-2d636abb22a3", "metadata": { "colab": { @@ -481,7 +463,7 @@ "GradeAnswer(binary_score='yes')" ] }, - "execution_count": 7, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -592,7 +574,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 11, "id": "b76b5ec3-0720-443d-85b1-c0e79659ca0a", "metadata": { "id": "b76b5ec3-0720-443d-85b1-c0e79659ca0a" @@ -681,26 +663,6 @@ " continue\n", " return {\"documents\": filtered_docs, \"question\": question}\n", "\n", - "def transform_query(state):\n", - " \"\"\"\n", - " Transform the query to produce a better question.\n", - "\n", - " Args:\n", - " state (dict): The current graph state\n", - "\n", - " Returns:\n", - " state (dict): Updates question key with a re-phrased question\n", - " \"\"\"\n", - "\n", - " print(\"---TRANSFORM QUERY---\")\n", - " question = state[\"question\"]\n", - " documents = state[\"documents\"]\n", - "\n", - " # Re-write question\n", - " print(\"WARNING: about to rewrite question but this shouldn't happen...\")\n", - " better_question = question_rewriter.invoke({\"question\": question})\n", - " return {\"documents\": documents, \"question\": better_question}\n", - "\n", "def web_search(state):\n", " \"\"\"\n", " Web search based on the re-phrased question.\n", @@ -832,7 +794,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 12, "id": "67854e07-9293-4c3c-bf9a-bc9a605570ee", "metadata": { "id": "67854e07-9293-4c3c-bf9a-bc9a605570ee" @@ -888,7 +850,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 13, "id": "29acc541-d726-4b75-84d1-a215845fe88a", "metadata": { "colab": { @@ -908,18 +870,13 @@ "\"Node 'web_search':\"\n", "'\\n---\\n'\n", "---GENERATE---\n", - "\"Node 'generate':\"\n", - "'\\n---\\n'\n", "---CHECK HALLUCINATIONS---\n", "---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---\n", "---GRADE GENERATION vs QUESTION---\n", "---DECISION: GENERATION ADDRESSES QUESTION---\n", - "\"Node '__end__':\"\n", + "\"Node 'generate':\"\n", "'\\n---\\n'\n", - "('Several sources expect the Chicago Bears to select USC quarterback Caleb '\n", - " 'Williams with their first pick in the 2024 NFL Draft. The Bears have two '\n", - " 'top-10 selections and the first overall pick is expected to be used on '\n", - " 'Williams.')\n" + "'The Bears are expected to draft Caleb Williams with their first pick.'\n" ] } ], @@ -946,12 +903,12 @@ "source": [ "Trace:\n", "\n", - "https://smith.langchain.com/public/09066150-24ec-4174-8551-7b31749899c4/r" + "https://smith.langchain.com/public/623da7bb-84a7-4e53-a63e-7ccd77fb9be5/r" ] }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 14, "id": "69a985dd-03c6-45af-a67b-b15746a2cb5f", "metadata": { "colab": { @@ -975,24 +932,18 @@ "---GRADE: DOCUMENT RELEVANT---\n", "---GRADE: DOCUMENT RELEVANT---\n", "---GRADE: DOCUMENT RELEVANT---\n", - "\"Node 'grade_documents':\"\n", - "'\\n---\\n'\n", "---ASSESS GRADED DOCUMENTS---\n", "---DECISION: GENERATE---\n", - "---GENERATE---\n", - "\"Node 'generate':\"\n", + "\"Node 'grade_documents':\"\n", "'\\n---\\n'\n", + "---GENERATE---\n", "---CHECK HALLUCINATIONS---\n", "---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---\n", "---GRADE GENERATION vs QUESTION---\n", "---DECISION: GENERATION ADDRESSES QUESTION---\n", - "\"Node '__end__':\"\n", + "\"Node 'generate':\"\n", "'\\n---\\n'\n", - "('There are three types of agent memory: sensory, short-term, and long-term. '\n", - " 'Sensory memory lasts for a few seconds and includes visual, auditory and '\n", - " 'touch impressions. Short-term memory lasts between 20 to 30 seconds and '\n", - " 'stores currently known information. Long-term memory can last up to decades '\n", - " 'and has an infinite capacity.')\n" + "'Sensory, short-term, and long-term memory.'\n" ] } ], @@ -1020,12 +971,12 @@ "source": [ "Trace:\n", "\n", - "https://smith.langchain.com/public/b630aca8-3417-4b0c-95d9-80a24c592c13/r" + "https://smith.langchain.com/public/57f3973b-6879-4fbe-ae31-9ae524c3a697/r" ] }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 15, "id": "qPwP_2PNiOjQ", "metadata": { "id": "qPwP_2PNiOjQ" @@ -1040,11 +991,8 @@ "---LLM Fallback---\n", "\"Node 'llm_fallback':\"\n", "'\\n---\\n'\n", - "\"Node '__end__':\"\n", - "'\\n---\\n'\n", - "(\"Hello! I'm doing well, thank you for asking. As an AI chatbot, I experience \"\n", - " 'no highs or lows and am always ready to assist you to the best of my '\n", - " 'abilities!')\n" + "(\"I don't have feelings as an AI assistant, but I'm here to help you with your \"\n", + " 'queries. How can I assist you today?')\n" ] } ], @@ -1063,10 +1011,20 @@ "pprint.pprint(value [\"generation\"])" ] }, + { + "cell_type": "markdown", + "id": "4107c8a4-6171-4c1b-840a-77a3d09f84fc", + "metadata": {}, + "source": [ + "Trace: \n", + "\n", + "https://smith.langchain.com/public/1f628ee4-8d2d-451e-aeb1-5d5e0ede2b4f/r" + ] + }, { "cell_type": "code", "execution_count": null, - "id": "dfaa345d-a829-4601-bb9a-392f06364f49", + "id": "ce3cda0a-c4bd-41ea-830b-d992f27fde15", "metadata": {}, "outputs": [], "source": []