add logo and discord to all notebooks (#636)

* add ppt rag notebook * verified notebooks * Delete docs/docs/examples/ppt_rag.ipynb * verified ppt notebook * add logo
tensorlakeai · May 31, 2024 · 1bb4b9c · 1bb4b9c
1 parent 3e2920b
commit 1bb4b9c
Show file tree

Hide file tree

Showing 20 changed files with 127 additions and 5 deletions.
diff --git a/docs/docs/examples/GifSearch.ipynb b/docs/docs/examples/GifSearch.ipynb
@@ -7,6 +7,12 @@
    "source": [
     "# **GIF search with MiniLM-L6 and CLIP embeddings**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "In this notebook, we'll create a semantic GIF search functionality with Indexify and Tumblr GIF dataset https://github.com/raingo/TGIF-Release. We'll use Indexify CLIP and MiniLM-L6 extractors to create embeddings for the GIFs and the search queries. We'll then use the embeddings to find the most similar GIFs to the search query."
    ]
   },

diff --git a/docs/docs/examples/HOA_Invoice_Data_Extraction.ipynb b/docs/docs/examples/HOA_Invoice_Data_Extraction.ipynb
@@ -6,6 +6,12 @@
    "source": [
     "# **Extracting Tabular Data from a PDF using Indexify**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "In this notebook, we're going to learn how we can extract transactional data from a PDF using Indexify. For that, we'll be using a sample PDF that contains transactional data from a Home Owners Association (HOA).\n",
     "\n",
     "We will explore several way to extract this data from the PDF using Indexify Extractor into a structured format that we can use further for RAG pipeline. This is the preview of the data that we will extract from the PDF.\n",

diff --git a/docs/docs/examples/Image_RAG_Structured_Extraction.ipynb b/docs/docs/examples/Image_RAG_Structured_Extraction.ipynb
@@ -7,6 +7,12 @@
    "source": [
     "# **Accurate Image RAG using Yolo and CodeGemma**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "Most Language Models(especially smaller ones) don't have vision capabilities. In this example, we will augment them with vision capabilities by automatically injecting structured data from images. The pipeline is tested to work at any scale, on laptops and with 10s of 1000s images on the cloud.\n",
     "\n",
     "What happens behind the scenes:\n",

diff --git a/docs/docs/examples/Instructor_RAG.ipynb b/docs/docs/examples/Instructor_RAG.ipynb
@@ -5,7 +5,13 @@
    "id": "defe2f2f",
    "metadata": {},
    "source": [
-    "## **Setup**"
+    "## **Setup**\n",
+    "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>"
    ]
   },
   {

diff --git a/docs/docs/examples/Invoices.ipynb b/docs/docs/examples/Invoices.ipynb
@@ -4,7 +4,13 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## **Setup**"
+        "## **Setup**\n",
+        "\n",
+        "<div class=\"align-center\">\n",
+        "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+        "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+        "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+        "</div>"
       ]
     },
     {

diff --git a/docs/docs/examples/Moondream_Visual_Description_Index.ipynb b/docs/docs/examples/Moondream_Visual_Description_Index.ipynb
@@ -7,6 +7,12 @@
    "source": [
     "# **Indexing Images Based on Visual Description**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "In this notebook we show how you can index images by visual description. We use a small visual description model called MoonDream. \n",
     "\n",
     "Once you setup Indexify, it will continoulsy extract visual descriptions using Moondream and index the description as images are ingested. You can build reliable applications which have to react to images in real-time. The use of such pipelines spans security, retail, and robotics."

diff --git a/docs/docs/examples/SEC_10_K_docs.ipynb b/docs/docs/examples/SEC_10_K_docs.ipynb
@@ -6,6 +6,12 @@
       "source": [
         "# **Introduction**\n",
         "\n",
+        "<div class=\"align-center\">\n",
+        "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+        "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+        "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+        "</div>\n",
+        "\n",
         "This notebook demonstrates how Indexify can make it easier to quickly extract insights from complex SEC filings like the Form 10-K annual report. Using Uber's 10-K as an example, we show how the Indexify library can enable question answering on the filing text to get rapid answers. We also illustrate how schema-based extraction can pull key data points from the unstructured document. The combination of question answering and schema-based extraction provides a powerful toolkit to derive insights from dense financial filings."
       ]
     },

diff --git a/docs/docs/examples/Scientific_Journals.ipynb b/docs/docs/examples/Scientific_Journals.ipynb
@@ -6,6 +6,12 @@
    "source": [
     "# Q and A on Scientific Journal\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "In this notebook we show text extraction from a scientific paper. We are going to chunk and embed the text after text extraction. We show Langchain based extraction."
    ]
   },

diff --git a/docs/docs/examples/Sixt.ipynb b/docs/docs/examples/Sixt.ipynb
@@ -5,6 +5,13 @@
    "metadata": {},
    "source": [
     "# **RAG on Multiple Terms and Conditions Documents Varying By Geography**\n",
+    "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "In this demo we are going to build a pipeline to build and update policy documents which vary by geography. \n",
     "\n",
     "Approach:\n",

diff --git a/docs/docs/examples/Terms_and_Condition_Documents_of_Car_Rental.ipynb b/docs/docs/examples/Terms_and_Condition_Documents_of_Car_Rental.ipynb
@@ -4,7 +4,13 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## **Setup**"
+        "## **Setup**\n",
+        "\n",
+        "<div class=\"align-center\">\n",
+        "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+        "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+        "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+        "</div>"
       ]
     },
     {

diff --git a/docs/docs/examples/Terms_and_Conditions_Documents_of_Health_Care_Benefits.ipynb b/docs/docs/examples/Terms_and_Conditions_Documents_of_Health_Care_Benefits.ipynb
@@ -4,7 +4,13 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## **Setup**"
+        "## **Setup**\n",
+        "\n",
+        "<div class=\"align-center\">\n",
+        "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+        "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+        "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+        "</div>"
       ]
     },
     {

diff --git a/docs/docs/examples/Video_RAG.ipynb b/docs/docs/examples/Video_RAG.ipynb
@@ -7,6 +7,12 @@
    "source": [
     "# **RAG using Video as Context**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "This notebook will guide you on creating a RAG pipeline with a video as the knowledge source. The pipeline will be able to answer questions based on the video content."
    ]
   },

diff --git a/docs/docs/examples/Visual_Understanding_Clip_Yolo.ipynb b/docs/docs/examples/Visual_Understanding_Clip_Yolo.ipynb
@@ -6,6 +6,13 @@
    "metadata": {},
    "source": [
     "# Querying Images using CLIP and YOLO\n",
+    "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "This notebook demonstrates creating CLIP embeddings to search images based on a text query and YOLO object detection allowing you to query images containing specific objects."
    ]
   },

diff --git a/docs/docs/examples/asrdiarization_rag.ipynb b/docs/docs/examples/asrdiarization_rag.ipynb
@@ -6,6 +6,12 @@
    "source": [
     "# **Transcribing Audio and Question Answering with ASR, Diarization, and Retrieval-Augmented Generation**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "This notebook demonstrates a powerful pipeline for transcribing audio, such as podcasts, and performing question answering using Retrieval-Augmented Generation (RAG). The pipeline combines Automatic Speech Recognition (ASR), diarization, and speculative decoding techniques to efficiently process audio data and generate informative responses.\n",
     "\n",
     "## Key Components\n",

diff --git a/docs/docs/examples/audio_rag.ipynb b/docs/docs/examples/audio_rag.ipynb
@@ -7,6 +7,12 @@
    "source": [
     "# **RAG using Audio as a Context**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "This notebook will show you how to use audio files as a context for your RAG pipeline. We are going to use 2 Indexify Extractors:\n",
     "\n",
     "- `tensorlake/whisper-asr`: This extractor will convert the audio file into text.\n",

diff --git a/docs/docs/examples/audio_transcription.ipynb b/docs/docs/examples/audio_transcription.ipynb
@@ -7,6 +7,12 @@
    "source": [
     "# **Transcribing Audio with Indexify**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "In this notebook, we will use an Indexify Extractor (Whisper ASR) to transcribe audio files to texts."
    ]
   },

diff --git a/docs/docs/examples/efficient_rag.ipynb b/docs/docs/examples/efficient_rag.ipynb
@@ -6,6 +6,12 @@
    "source": [
     "# Efficient and supercharged RAG for mixed context texts with Indexify's framework, Gemini's 1M context & Arctic's embeddings\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "## Introduction\n",
     "\n",
     "Retrieval-augmented generation (RAG) systems have emerged as a groundbreaking approach in natural language processing, enabling the generation of accurate and contextually relevant responses by leveraging external knowledge. These systems have the potential to revolutionize various applications, from question answering and content generation to dialogue systems and beyond. However, despite their immense promise, modern RAG systems face a significant challenge when it comes to efficiently processing large mixed context texts.\n",

diff --git a/docs/docs/examples/pdfqa.ipynb b/docs/docs/examples/pdfqa.ipynb
@@ -6,6 +6,12 @@
    "source": [
     "## **Installation and Setup**\n",
     "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>\n",
+    "\n",
     "1. Install the `indexify-extractor-sdk` package using pip."
    ]
   },

diff --git a/docs/docs/examples/ppt_rag.ipynb b/docs/docs/examples/ppt_rag.ipynb
@@ -6,6 +6,12 @@
       "source": [
         "# **Introduction**\n",
         "\n",
+        "<div class=\"align-center\">\n",
+        "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+        "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+        "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+        "</div>\n",
+        "\n",
         "This notebook demonstrates how Indexify can make it easier to quickly extract insights from complex real-world PowerPoint presentations like a talk given on \"[A little guide to building Large Language Models in 2024](https://docs.google.com/presentation/d/1IkzESdOwdmwvPxIELYJi8--K3EZ98_cL6c5ZcLKSyVg/edit?usp=sharing)\" by Thomas, the co-founder of Hugging Face. Using the slides as an example, we show how the Indexify library can enable question answering on the talk to get rapid answers."
       ]
     },

diff --git a/docs/docs/examples/rag.ipynb b/docs/docs/examples/rag.ipynb
@@ -5,7 +5,13 @@
    "id": "2a784b7a",
    "metadata": {},
    "source": [
-    "## **Setup**"
+    "## **Setup**\n",
+    "\n",
+    "<div class=\"align-center\">\n",
+    "  <a href=\"https://getindexify.ai/\"><img src=\"https://getindexify.ai/Indexify_Logo_Wordmark.svg\" width=\"145\"></a>\n",
+    "  <a href=\"https://discord.com/invite/kF8UZACA7r\"><img src=\"https://raw.githubusercontent.com/rishiraj/random/main/Discord%20button.png\" width=\"145\"></a><br>\n",
+    "  Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/tensorlakeai/indexify\">Github</a></i> ⭐\n",
+    "</div>"
    ]
   },
   {