From 5435ff6f7f1f8d3f73da4e91d3d65e9f8bde6d56 Mon Sep 17 00:00:00 2001 From: Lance Martin Date: Sun, 26 May 2024 15:14:04 -0700 Subject: [PATCH] Minor change to upgrade libs --- examples/rag/langgraph_self_rag.ipynb | 76 ++++++++++++++------------- 1 file changed, 40 insertions(+), 36 deletions(-) diff --git a/examples/rag/langgraph_self_rag.ipynb b/examples/rag/langgraph_self_rag.ipynb index 99f826673..a10fb5928 100644 --- a/examples/rag/langgraph_self_rag.ipynb +++ b/examples/rag/langgraph_self_rag.ipynb @@ -60,7 +60,7 @@ "metadata": {}, "outputs": [], "source": [ - "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph" + "! pip install -U langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph" ] }, { @@ -159,10 +159,18 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 2, "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", @@ -215,7 +223,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 3, "id": "dcd77cc1-4587-40ec-b633-5364eab9e1ec", "metadata": {}, "outputs": [ @@ -223,7 +231,7 @@ "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. 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 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" ] } ], @@ -255,7 +263,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 4, "id": "e78931ec-940c-46ad-a0b2-f43f953f1fd7", "metadata": {}, "outputs": [ @@ -265,7 +273,7 @@ "GradeHallucinations(binary_score='yes')" ] }, - "execution_count": 7, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -303,7 +311,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 5, "id": "bd62276f-bf26-40d0-8cff-e07b10e00321", "metadata": {}, "outputs": [ @@ -313,7 +321,7 @@ "GradeAnswer(binary_score='yes')" ] }, - "execution_count": 8, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -403,7 +411,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 7, "id": "f1617e9e-66a8-4c1a-a1fe-cc936284c085", "metadata": {}, "outputs": [], @@ -429,7 +437,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 8, "id": "add509d8-6682-4127-8d95-13dd37d79702", "metadata": {}, "outputs": [], @@ -609,7 +617,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 10, "id": "0e09ca9f-e36d-4ef4-a0d5-79fdbada9fe0", "metadata": {}, "outputs": [], @@ -645,14 +653,14 @@ " \"not useful\": \"transform_query\",\n", " },\n", ")\n", - "ß\n", + "\n", "# Compile\n", "app = workflow.compile()" ] }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 11, "id": "fb69dbb9-91ee-4868-8c3c-93af3cd885be", "metadata": {}, "outputs": [ @@ -668,24 +676,22 @@ "---GRADE: DOCUMENT RELEVANT---\n", "---GRADE: DOCUMENT NOT 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", - "('Short-term memory is used for in-context learning and lasts for a short '\n", - " 'period, while long-term memory allows the agent to retain and recall '\n", - " 'information over extended periods. Agents can also utilize external tools '\n", - " 'like APIs to access additional information not stored in their model '\n", - " 'weights.')\n" + "('Short-term memory is used for in-context learning in agents, allowing them '\n", + " 'to learn quickly. Long-term memory enables agents to retain and recall vast '\n", + " 'amounts of information over extended periods. Agents can also utilize '\n", + " 'external tools like APIs to access additional information beyond what is '\n", + " 'stored in their memory.')\n" ] } ], @@ -708,7 +714,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 12, "id": "4138bc51-8c84-4b8a-8d24-f7f470721f6f", "metadata": {}, "outputs": [ @@ -721,28 +727,26 @@ "'\\n---\\n'\n", "---CHECK DOCUMENT RELEVANCE TO QUESTION---\n", "---GRADE: DOCUMENT RELEVANT---\n", + "---GRADE: DOCUMENT NOT RELEVANT---\n", "---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", - "('Chain of thought prompting works by providing a series of prompts or '\n", - " 'demonstrations to guide the model through a reasoning process. This method '\n", - " 'involves iteratively constructing thought processes by asking follow-up '\n", - " 'questions or exploring multiple reasoning possibilities at each step. '\n", - " 'External search queries and relevant content from sources like Wikipedia can '\n", - " 'be integrated into the context to enhance the chain of thought reasoning.')\n" + "('Chain of thought prompting works by repeatedly prompting the model to ask '\n", + " 'follow-up questions to construct the thought process iteratively. This '\n", + " 'method can be combined with queries to search for relevant entities and '\n", + " 'content to add back into the context. It extends the thought process by '\n", + " 'exploring multiple reasoning possibilities at each step, creating a tree '\n", + " 'structure of thoughts.')\n" ] } ],