From 696867f7bd7333e0a82cafe8f14a2e65407633a6 Mon Sep 17 00:00:00 2001 From: ErikaPark Date: Thu, 9 Jan 2025 23:43:42 +0900 Subject: [PATCH] Fix incorrect file path --- 10-Retriever/01-VectorStoreRetriever.ipynb | 44 +++++++++++++--------- 1 file changed, 27 insertions(+), 17 deletions(-) diff --git a/10-Retriever/01-VectorStoreRetriever.ipynb b/10-Retriever/01-VectorStoreRetriever.ipynb index a6fa37e0..8ff21da4 100644 --- a/10-Retriever/01-VectorStoreRetriever.ipynb +++ b/10-Retriever/01-VectorStoreRetriever.ipynb @@ -139,6 +139,16 @@ ")" ] }, + { + "cell_type": "markdown", + "id": "90c24f41", + "metadata": {}, + "source": [ + "You can alternatively set API keys such as `OPENAI_API_KEY` in a `.env` file and load them.\n", + "\n", + "[Note] This is not necessary if you've already set the required API keys in previous steps." + ] + }, { "cell_type": "code", "execution_count": 4, @@ -218,7 +228,7 @@ "from langchain_community.document_loaders import TextLoader\n", "\n", "# Load the file using TextLoader\n", - "loader = TextLoader(\"./assets/01-vectorstore-retriever-appendix-keywords.txt\", encoding=\"utf-8\")\n", + "loader = TextLoader(\"./data/01-vectorstore-retriever-appendix-keywords.txt\", encoding=\"utf-8\")\n", "documents = loader.load()\n", "\n", "# split the text into chunks\n", @@ -493,7 +503,7 @@ "📄 Document Content: Definition: A DataFrame is a tabular data structure with rows and columns, commonly used for data analysis and manipulation.\n", "Example: Pandas DataFrame can store data like an Excel sheet and perform operations like filtering and grouping.\n", "Related Keywords: Data Analysis, Pandas, Data Manipulation\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "\n", "🔍 [Search Result 2]\n", @@ -504,7 +514,7 @@ "Related Keywords: Database, Data Modeling, Data Management\n", "\n", "DataFrame\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "\n", "🔍 [Search Result 3]\n", @@ -513,12 +523,12 @@ "Definition: Pandas is a Python library for data analysis and manipulation, offering tools for working with structured data.\n", "Example: Pandas can read CSV files, clean data, and perform statistical analysis.\n", "Related Keywords: Data Analysis, Python, Data Manipulation\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "\n", "🔍 [Search Result 4]\n", "📄 Document Content: Data Mining\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n" ] } @@ -584,17 +594,17 @@ "\n", "📄 [Document 1]\n", "📖 Document Content: Embedding\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "📄 [Document 2]\n", "📖 Document Content: Definition: Embedding is the process of converting text data, such as words or sentences, into continuous low-dimensional vectors. This allows computers to understand and process text.\n", "Example: The word \"apple\" can be represented as a vector like [0.65, -0.23, 0.17].\n", "Related Keywords: Natural Language Processing, Vectorization, Deep Learning\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "📄 [Document 3]\n", "📖 Document Content: TF-IDF (Term Frequency-Inverse Document Frequency)\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n" ] } @@ -658,25 +668,25 @@ "Definition: Word2Vec is a technique in NLP that maps words into a vector space, representing their semantic relationships based on context.\n", "Example: In Word2Vec, \"king\" and \"queen\" would be represented by vectors close to each other.\n", "Related Keywords: NLP, Embeddings, Semantic Similarity\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "📄 [Document 2]\n", "📖 Document Content: Definition: Embedding is the process of converting text data, such as words or sentences, into continuous low-dimensional vectors. This allows computers to understand and process text.\n", "Example: The word \"apple\" can be represented as a vector like [0.65, -0.23, 0.17].\n", "Related Keywords: Natural Language Processing, Vectorization, Deep Learning\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "📄 [Document 3]\n", "📖 Document Content: TF-IDF (Term Frequency-Inverse Document Frequency)\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "📄 [Document 4]\n", "📖 Document Content: Tokenizer\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "📄 [Document 5]\n", "📖 Document Content: Semantic Search\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n" ] } @@ -734,7 +744,7 @@ "\n", "📄 [Document 1]\n", "📖 Document Content: Embedding\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n" ] } @@ -1020,7 +1030,7 @@ "from langchain_upstage import UpstageEmbeddings\n", "\n", "# ✅ 1. Data Loading and Document Splitting\n", - "loader = TextLoader(\"./assets/01-vectorstore-retriever-appendix-keywords.txt\", encoding=\"utf-8\")\n", + "loader = TextLoader(\"./data/01-vectorstore-retriever-appendix-keywords.txt\", encoding=\"utf-8\")\n", "documents = loader.load()\n", "\n", "# Split the loaded documents into text chunks \n", @@ -1057,13 +1067,13 @@ "\n", "📄 [Document 1]\n", "📖 Document Content: Embedding\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n", "📄 [Document 2]\n", "📖 Document Content: Definition: Embedding is the process of converting text data, such as words or sentences, into continuous low-dimensional vectors. This allows computers to understand and process text.\n", "Example: The word \"apple\" can be represented as a vector like [0.65, -0.23, 0.17].\n", "Related Keywords: Natural Language Processing, Vectorization, Deep Learning\n", - "🗂️ Metadata: {'source': './assets/01-vectorstore-retriever-appendix-keywords.txt'}\n", + "🗂️ Metadata: {'source': './data/01-vectorstore-retriever-appendix-keywords.txt'}\n", "============================================================\n" ] }