Merge pull request #4 from Qredence/main

Merging
Qredence · Jul 22, 2024 · 631a31e · 631a31e
2 parents 681f1c8 + 2c680a6
commit 631a31e
Show file tree

Hide file tree

Showing 6 changed files with 425 additions and 152 deletions.
diff --git a/graphfleet/tools/convert_pdfs_to_txt.py b/graphfleet/tools/convert_pdfs_to_txt.py
@@ -0,0 +1,23 @@
+import os
+from PyPDF2 import PdfReader
+
+# Directory containing PDF files
+directory = 'graphfleet/input/pdf'
+
+# Function to convert PDF to text
+def convert_pdf_to_txt(pdf_path, txt_path):
+    with open(pdf_path, 'rb') as pdf_file:
+        reader = PdfReader(pdf_file)
+        text = ''
+        for page_num in range(len(reader.pages)):
+            text += reader.pages[page_num].extract_text()
+        with open(txt_path, 'w', encoding='utf-8') as txt_file:
+            txt_file.write(text)
+
+# Loop through all PDF files in the directory
+for filename in os.listdir(directory):
+    if filename.endswith('.pdf'):
+        pdf_path = os.path.join(directory, filename)
+        txt_path = os.path.join(directory, filename.replace('.pdf', '.txt'))
+        convert_pdf_to_txt(pdf_path, txt_path)
+        print(f'Converted {filename} to text.')
diff --git a/notebook/get-started-graphfleet.ipynb b/notebook/get-started-graphfleet.ipynb
@@ -1,25 +1,18 @@
 {
  "cells": [
   {
-   "cell_type": "code",
-   "execution_count": 2,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[31;1mNo module named 'packaging'\u001b[39;22m\n",
-      "\n",
-      "\u001b[31;1mNo module named 'packaging'\u001b[39;22m\n"
-     ]
-    }
-   ],
    "source": [
-    "! poetry shell\n",
-    "! poetry install\n"
+    "To use "
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

diff --git a/notebook/graph-visualization.ipynb b/notebook/graph-visualization.ipynb
@@ -78,11 +78,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
-    "INPUT_DIR = \"/Volumes/Samsung-SSD-T7/Qredence/_Poetry/AgenticFleetPackage/GraphFleetProd/graphfleet/output/20240719-023135/artifacts\"\n",
+    "INPUT_DIR = \"../graphfleet/output/20240719-023135/artifacts\"\n",
     "LANCEDB_URI = f\"{INPUT_DIR}/lancedb\"\n",
     "\n",
     "COMMUNITY_REPORT_TABLE = \"create_final_community_reports\"\n",
@@ -103,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -121,7 +121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -142,13 +142,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.1.2\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
       "Note: you may need to restart the kernel to use updated packages.\n"
      ]
     }
@@ -232,7 +235,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -288,7 +291,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -305,13 +308,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "dea34c63aa48405294956a6822606b01",
+       "model_id": "ab94d989dbee4ddf91c369abd430399b",
        "version_major": 2,
        "version_minor": 0
       },

diff --git a/notebook/local_search.ipynb b/notebook/local_search.ipynb
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -74,7 +74,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "INPUT_DIR = \"/Volumes/Samsung-SSD-T7/Qredence/_Poetry/AgenticFleetPackage/GraphFleetProd/graphfleet/output/20240719-023135/artifacts\"\n",
+    "INPUT_DIR = \"../graphfleet/output/20240719-023135/artifacts\"\n",
     "LANCEDB_URI = f\"{INPUT_DIR}/lancedb\"\n",
     "\n",
     "COMMUNITY_REPORT_TABLE = \"create_final_community_reports\"\n",