diff --git a/docs/docs_skeleton/docs/use_cases/web_scraping/index.mdx b/docs/docs_skeleton/docs/use_cases/web_scraping/index.mdx deleted file mode 100644 index 0adf1130b7..0000000000 --- a/docs/docs_skeleton/docs/use_cases/web_scraping/index.mdx +++ /dev/null @@ -1,5 +0,0 @@ -# Web Scraping - -Web scraping has historically been a challenging endeavor due to the ever-changing nature of website structures, making it tedious for developers to maintain their scraping scripts. Traditional methods often rely on specific HTML tags and patterns which, when altered, can disrupt data extraction processes. - -Enter the LLM-based method for parsing HTML: By leveraging the capabilities of LLMs, and especially OpenAI Functions in LangChain's extraction chain, developers can instruct the model to extract only the desired data in a specified format. This method not only streamlines the extraction process but also significantly reduces the time spent on manual debugging and script modifications. Its adaptability means that even if websites undergo significant design changes, the extraction remains consistent and robust. This level of resilience translates to reduced maintenance efforts, cost savings, and ensures a higher quality of extracted data. Compared to its predecessors, the LLM-based approach wins out in the web scraping domain by transforming a historically cumbersome task into a more automated and efficient process. diff --git a/docs/extras/use_cases/apis.ipynb b/docs/extras/use_cases/apis.ipynb index 1af0a7f3ce..8d9259c3ca 100644 --- a/docs/extras/use_cases/apis.ipynb +++ b/docs/extras/use_cases/apis.ipynb @@ -1,12 +1,21 @@ { "cells": [ + { + "cell_type": "raw", + "id": "ea5c61b2-8b52-4270-bdb0-c4df88608f15", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: Interacting with APIs\n", + "---" + ] + }, { "cell_type": "markdown", "id": "a15e6a18", "metadata": {}, "source": [ - "# Interacting with APIs\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/apis.ipynb)\n", "\n", "## Use case \n", @@ -69,9 +78,7 @@ "cell_type": "code", "execution_count": 2, "id": "30b780e3", - "metadata": { - "scrolled": false - }, + "metadata": {}, "outputs": [ { "name": "stderr", @@ -415,7 +422,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.16" + "version": "3.9.1" } }, "nbformat": 4, diff --git a/docs/extras/use_cases/chatbots.ipynb b/docs/extras/use_cases/chatbots.ipynb index 58e3ce5317..c67d595c9f 100644 --- a/docs/extras/use_cases/chatbots.ipynb +++ b/docs/extras/use_cases/chatbots.ipynb @@ -1,12 +1,21 @@ { "cells": [ + { + "cell_type": "raw", + "id": "22fd28c9-9b48-476c-bca8-20efef7fdb14", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: Chatbots\n", + "---" + ] + }, { "cell_type": "markdown", "id": "ee7f95e4", "metadata": {}, "source": [ - "# Chatbots\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/chatbots.ipynb)\n", "\n", "## Use case\n", diff --git a/docs/extras/use_cases/code_understanding.ipynb b/docs/extras/use_cases/code_understanding.ipynb index 60a02b9bb3..df0cfbf9d1 100644 --- a/docs/extras/use_cases/code_understanding.ipynb +++ b/docs/extras/use_cases/code_understanding.ipynb @@ -1,11 +1,19 @@ { "cells": [ + { + "cell_type": "raw", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: Code understanding\n", + "---" + ] + }, { "cell_type": "markdown", "metadata": {}, "source": [ - "# Code Understanding\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/code_understanding.ipynb)\n", "\n", "## Use case\n", @@ -1047,7 +1055,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.16" + "version": "3.9.1" } }, "nbformat": 4, diff --git a/docs/extras/use_cases/extraction.ipynb b/docs/extras/use_cases/extraction.ipynb index 7aaa37f046..628026127a 100644 --- a/docs/extras/use_cases/extraction.ipynb +++ b/docs/extras/use_cases/extraction.ipynb @@ -1,12 +1,21 @@ { "cells": [ + { + "cell_type": "raw", + "id": "df29b30a-fd27-4e08-8269-870df5631f9e", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: Extraction\n", + "---" + ] + }, { "cell_type": "markdown", "id": "b84edb4e", "metadata": {}, "source": [ - "# Extraction\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/extraction.ipynb)\n", "\n", "## Use case\n", @@ -589,7 +598,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.16" + "version": "3.9.1" } }, "nbformat": 4, diff --git a/docs/extras/use_cases/more/_category_.yml b/docs/extras/use_cases/more/_category_.yml index ee76dee18f..53055fb940 100644 --- a/docs/extras/use_cases/more/_category_.yml +++ b/docs/extras/use_cases/more/_category_.yml @@ -1 +1,2 @@ label: 'More' +position: 2 \ No newline at end of file diff --git a/docs/extras/use_cases/sql.ipynb b/docs/extras/use_cases/sql.ipynb index 0a047779f8..02eab3db4c 100644 --- a/docs/extras/use_cases/sql.ipynb +++ b/docs/extras/use_cases/sql.ipynb @@ -1,11 +1,19 @@ { "cells": [ + { + "cell_type": "raw", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: SQL\n", + "---" + ] + }, { "cell_type": "markdown", "metadata": {}, "source": [ - "# SQL\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/sql.ipynb)\n", "\n", "## Use case\n", @@ -856,9 +864,7 @@ { "cell_type": "code", "execution_count": 23, - "metadata": { - "scrolled": false - }, + "metadata": {}, "outputs": [ { "name": "stdout", @@ -1014,9 +1020,7 @@ { "cell_type": "code", "execution_count": 55, - "metadata": { - "scrolled": false - }, + "metadata": {}, "outputs": [ { "name": "stdout", @@ -1256,7 +1260,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.17" + "version": "3.9.1" } }, "nbformat": 4, diff --git a/docs/extras/use_cases/summarization.ipynb b/docs/extras/use_cases/summarization.ipynb index 000ba48124..6d7e118ab7 100644 --- a/docs/extras/use_cases/summarization.ipynb +++ b/docs/extras/use_cases/summarization.ipynb @@ -1,12 +1,21 @@ { "cells": [ + { + "cell_type": "raw", + "id": "2aca8168-62ec-4bba-93f0-73da08cd1920", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: Summarization\n", + "---" + ] + }, { "cell_type": "markdown", "id": "cf13f702", "metadata": {}, "source": [ - "# Summarization\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/summarization.ipynb)\n", "\n", "## Use case\n", @@ -548,7 +557,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.16" + "version": "3.9.1" } }, "nbformat": 4, diff --git a/docs/extras/use_cases/tagging.ipynb b/docs/extras/use_cases/tagging.ipynb index 235f9d06cb..37242a84f5 100644 --- a/docs/extras/use_cases/tagging.ipynb +++ b/docs/extras/use_cases/tagging.ipynb @@ -1,12 +1,21 @@ { "cells": [ + { + "cell_type": "raw", + "id": "cb6f552e-775f-4d84-bc7c-dca94c06a33c", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: Tagging\n", + "---" + ] + }, { "cell_type": "markdown", "id": "a0507a4b", "metadata": {}, "source": [ - "# Tagging\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/tagging.ipynb)\n", "\n", "## Use case\n", @@ -408,7 +417,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.16" + "version": "3.9.1" } }, "nbformat": 4, diff --git a/docs/extras/use_cases/web_scraping.ipynb b/docs/extras/use_cases/web_scraping.ipynb index 57c9e8387a..41bb28703e 100644 --- a/docs/extras/use_cases/web_scraping.ipynb +++ b/docs/extras/use_cases/web_scraping.ipynb @@ -1,12 +1,21 @@ { "cells": [ + { + "cell_type": "raw", + "id": "e254cf03-49fc-4051-a4df-3a8e4e7d2688", + "metadata": {}, + "source": [ + "---\n", + "sidebar_position: 1\n", + "title: Web scraping\n", + "---" + ] + }, { "cell_type": "markdown", "id": "6605e7f7", "metadata": {}, "source": [ - "# Web Scraping\n", - "\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/web_scraping.ipynb)\n", "\n", "## Use case\n", @@ -306,9 +315,7 @@ "cell_type": "code", "execution_count": 7, "id": "977560ba", - "metadata": { - "scrolled": false - }, + "metadata": {}, "outputs": [ { "name": "stdout", @@ -591,7 +598,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.16" + "version": "3.9.1" } }, "nbformat": 4,