image pipeline perfected. audio pipeline in progress
This commit is contained in:
timothyafolami
@@ -1,3 +1,4 @@
|
||||
Ai indexing
|
||||
data
|
||||
images
|
||||
.env
|
||||
@@ -0,0 +1,135 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install groq"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from groq import Groq\n",
|
||||
"import os\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"client = Groq(api_key = os.getenv('GROQ_API_KEY'))\n",
|
||||
"model = 'whisper-large-v3'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Audio to Text\n",
|
||||
"def audio_to_text(filepath):\n",
|
||||
" with open(filepath, \"rb\") as file:\n",
|
||||
" translation = client.audio.translations.create(\n",
|
||||
" file=(filepath, file.read()),\n",
|
||||
" model=\"whisper-large-v3\",\n",
|
||||
" )\n",
|
||||
" return translation.text"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "APIStatusError",
|
||||
"evalue": "Error code: 413 - {'error': {'message': 'Request Entity Too Large', 'type': 'invalid_request_error', 'code': 'request_too_large'}}",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mAPIStatusError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[10], line 3\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m# testing the function\u001b[39;00m\n\u001b[0;32m 2\u001b[0m path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdata/audio-1.mp3\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m----> 3\u001b[0m transcript \u001b[38;5;241m=\u001b[39m \u001b[43maudio_to_text\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m)\u001b[49m\n",
|
||||
"Cell \u001b[1;32mIn[6], line 4\u001b[0m, in \u001b[0;36maudio_to_text\u001b[1;34m(filepath)\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21maudio_to_text\u001b[39m(filepath):\n\u001b[0;32m 3\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(filepath, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m file:\n\u001b[1;32m----> 4\u001b[0m translation \u001b[38;5;241m=\u001b[39m \u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43maudio\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtranslations\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43mfile\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mfilepath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfile\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mwhisper-large-v3\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 8\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m translation\u001b[38;5;241m.\u001b[39mtext\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\resources\\audio\\translations.py:103\u001b[0m, in \u001b[0;36mTranslations.create\u001b[1;34m(self, file, model, prompt, response_format, temperature, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[0;32m 98\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m files:\n\u001b[0;32m 99\u001b[0m \u001b[38;5;66;03m# It should be noted that the actual Content-Type header that will be\u001b[39;00m\n\u001b[0;32m 100\u001b[0m \u001b[38;5;66;03m# sent to the server will contain a `boundary` parameter, e.g.\u001b[39;00m\n\u001b[0;32m 101\u001b[0m \u001b[38;5;66;03m# multipart/form-data; boundary=---abc--\u001b[39;00m\n\u001b[0;32m 102\u001b[0m extra_headers \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mContent-Type\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmultipart/form-data\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m(extra_headers \u001b[38;5;129;01mor\u001b[39;00m {})}\n\u001b[1;32m--> 103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 104\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/openai/v1/audio/translations\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m 105\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtranslation_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTranslationCreateParams\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 106\u001b[0m \u001b[43m \u001b[49m\u001b[43mfiles\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfiles\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 107\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 108\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[0;32m 109\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 110\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mTranslation\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 111\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\_base_client.py:1225\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[1;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[0;32m 1211\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[0;32m 1212\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 1213\u001b[0m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1220\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m 1221\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[0;32m 1222\u001b[0m opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[0;32m 1223\u001b[0m method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[0;32m 1224\u001b[0m )\n\u001b[1;32m-> 1225\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\_base_client.py:920\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[1;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[0;32m 911\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[0;32m 912\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 913\u001b[0m cast_to: Type[ResponseT],\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 918\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m 919\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m--> 920\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 921\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 922\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 923\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 924\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 925\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 926\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\_base_client.py:960\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[1;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[0;32m 957\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEncountered httpx.TimeoutException\u001b[39m\u001b[38;5;124m\"\u001b[39m, exc_info\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 959\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m--> 960\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 961\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 962\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 963\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 964\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 965\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 966\u001b[0m \u001b[43m \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m 967\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 969\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRaising timeout error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 970\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m APITimeoutError(request\u001b[38;5;241m=\u001b[39mrequest) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\_base_client.py:1051\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[1;34m(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)\u001b[0m\n\u001b[0;32m 1047\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[0;32m 1048\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[0;32m 1049\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[1;32m-> 1051\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 1052\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1053\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1054\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1055\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1056\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1057\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\_base_client.py:975\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[1;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[0;32m 972\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEncountered Exception\u001b[39m\u001b[38;5;124m\"\u001b[39m, exc_info\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 974\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m--> 975\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 976\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 977\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 978\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 979\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 980\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 981\u001b[0m \u001b[43m \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m 982\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 984\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRaising connection error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 985\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m APIConnectionError(request\u001b[38;5;241m=\u001b[39mrequest) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\_base_client.py:1051\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[1;34m(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)\u001b[0m\n\u001b[0;32m 1047\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[0;32m 1048\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[0;32m 1049\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[1;32m-> 1051\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 1052\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1053\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1054\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1055\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1056\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1057\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
|
||||
"File \u001b[1;32mc:\\Users\\timmy_3aupohg\\anaconda3\\envs\\smog_env\\Lib\\site-packages\\groq\\_base_client.py:1018\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[1;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[0;32m 1015\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[0;32m 1017\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m-> 1018\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m 1020\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[0;32m 1021\u001b[0m cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[0;32m 1022\u001b[0m options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1025\u001b[0m stream_cls\u001b[38;5;241m=\u001b[39mstream_cls,\n\u001b[0;32m 1026\u001b[0m )\n",
|
||||
"\u001b[1;31mAPIStatusError\u001b[0m: Error code: 413 - {'error': {'message': 'Request Entity Too Large', 'type': 'invalid_request_error', 'code': 'request_too_large'}}"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# testing the function\n",
|
||||
"path = \"data/audio-1.mp3\"\n",
|
||||
"transcript = audio_to_text(path)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" hello everyone so i'm timothy i'm doing this recording to talk about something i need about cars okay let's say very correct okay so what is a car the guy is a mechanical object designed to transport people from one location to the other so that's like how i would define a car for you right okay so what do i need about a car how do i fix something I kind of know little and that little is a much on its own right I have very good understanding of like service is very cool, a car, you know changing the oil, removing the oil filter, changing the oil filter like that like that right so I think um yeah yeah yeah yeah so what else you don't see what else should I say? alright this is good it's good enough yeah thanks bye stop\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(transcript)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "smog_env",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
||||
+1
-1
@@ -1 +1 @@
|
||||
{"doc_names": ["Car-Repair-Receipt-repair", "Car-Repair-Receipt-service", "Car-Repair-Receipt-tire", "Car-Repair-Receipt-tuning", "Car-Repair-Receipt-wash", "corolla-2020-toyota-owners-manual", "data\\dodge-challenger-auto-body-repair-after", "data\\dodge-challenger-auto-body-repair-before", "How to change engine oil and filter on TOYOTA Corolla", "How to change front brake pads on TOYOTA Corolla", "How to change rear windshield wipers on TOYOTA Corolla", "How to change spark plugs on TOYOTA COROLLA", "data\\hyundai-sonata-auto-body-repair-after", "data\\hyundai-sonata-auto-body-repair-before", "data\\IMG_1436", "data\\IMG_1437", "data\\IMG_1438", "data\\IMG_1440", "data\\IMG_1441", "data\\IMG_1442", "data\\IMG_1443", "data\\IMG_1444", "data\\pontiac-vibe-auto-body-repair-after", "data\\pontiac-vibe-auto-body-repair-before", "data\\toyota-tacoma-auto-body-repair-after", "data\\toyota-tacoma-auto-body-repair-before"], "docs_id": ["5f26879376a44a77bbc2b966b9189ca4", "51b1c6cab5f1440e9fd948b6d858e812", "1d63ef4a149d4addb0803370885d70c1", "749ea365f2244eb6b23bb17e28d9cd2e", "e6d3736c0e8f424382c2ff5298814534", "91b116993e4b4865b3dc7bceca9749f0", "77f9558bd9894daeaf9aaea4013ed20e", "d974631f67d242739343b3c32e91355c", "a18ad23b3c7641b3a61e77e0e143a265", "0b710683db314b14ae6f0e0919a12068", "136c808efffa4f8798c55e7595c768a1", "236dc9603c9c4e83840721175d3dc861", "5aa9f750dbdd403c94abb53883c0fad2", "0382e54d68a84021803b07c7cf7c3ad9", "a772d008c9bf4ee6a2026f00998f3f2c", "66afb44563f6449ca705a39c9a72440d", "59ef1e9cc81b41d3a32d5dcc069a0ace", "9991145202384596bc3f5ff666d213bd", "d7f49b6629e84ec7bfd1a0048d2ade76", "689296161d6b46e8b9e792dbdc8a155d", "ba6be2ab8ae74042a9c9da51c46b8f90", "d62daf66b833419fae17333395cd7b04", "7b109e03c62343fd8f8e23dcf6bdfd3b", "8254386611fc4feb85744f69e5120e18", "022d6bae08274a618921c49590040a1f", "719ed0e4d9a94fe39799c227eaac1e05"], "num_pages": [1, 2, 2, 2, 1, 588, 1, 1, 6, 7, 6, 10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}
|
||||
{"doc_names": ["Car-Repair-Receipt-repair", "Car-Repair-Receipt-service", "Car-Repair-Receipt-tire", "Car-Repair-Receipt-tuning", "Car-Repair-Receipt-wash", "corolla-2020-toyota-owners-manual", "data\\dodge-challenger-auto-body-repair-after", "data\\dodge-challenger-auto-body-repair-before", "How to change engine oil and filter on TOYOTA Corolla", "How to change front brake pads on TOYOTA Corolla", "How to change rear windshield wipers on TOYOTA Corolla", "How to change spark plugs on TOYOTA COROLLA", "data\\hyundai-sonata-auto-body-repair-after", "data\\hyundai-sonata-auto-body-repair-before", "data\\IMG_1436", "data\\IMG_1437", "data\\IMG_1438", "data\\IMG_1440", "data\\IMG_1441", "data\\IMG_1442", "data\\IMG_1443", "data\\IMG_1444", "data\\pontiac-vibe-auto-body-repair-after", "data\\pontiac-vibe-auto-body-repair-before", "data\\toyota-tacoma-auto-body-repair-after", "data\\toyota-tacoma-auto-body-repair-before"], "docs_id": ["8cb89c7137934d26bb4d277bacf3502c", "b71d912e8f2e487ebe8234e5b115261a", "85899825f6564cd2ace41045b9b3933a", "0f4160aa7a7544b9912203707684b580", "5dfef1a8108d42239dfacb145ff65b47", "cf8d2cd0ff2e41f28c6ca6e831ac11e0", "9f13671afa5b4572b3d87a974e9ae987", "b61bf58bed3441b98d017a8273592a6e", "2d60dcf3360a4d3f8bdf26ae7d7a7710", "c041d9b8d4d34845b1eec7076b9e397a", "51dfede7f1424c9a860aa6d0ac2aba9d", "9d5ae90bdb2f42c9a4a7eff8222f9299", "38e241f38b964f6598f68a7bdc7d6fd0", "3e28189980ef48e3924225a4795ee4f6", "b503ccb23a6140e4b3479cd0540bc7db", "56a6e12c0f4e492abf84ed420332dd53", "278b4e52edae4a34be3e6ac8b8c6fea0", "16b5cb0fd5994cb3b05881c2bd7f079b", "4f26ca03b4f74f0287cb4ec163d8a8fe", "74987f862eaf43008779404633d00352", "db78336a07d3424badbb508bdbc951dd", "4c993794c7244ce6a29bb4a6e36b035f", "004cceb280574f818e3f654bb70539ab", "a1f5ec1368c845e3b8f6c31fb7116238", "d193544fc7ce45139b3f1e85d9edbde2", "06c837414be84b49b84b505628927814"], "num_pages": [1, 2, 2, 2, 1, 588, 1, 1, 6, 7, 6, 10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}
|
||||
Binary file not shown.
+70
-3
@@ -11,6 +11,13 @@ from langchain_core.documents import Document
|
||||
from text_extractor import TextExtractor
|
||||
import os
|
||||
import json
|
||||
import base64
|
||||
import requests
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv()
|
||||
|
||||
# OpenAI API Key
|
||||
api_key = os.getenv('OPENAI_API_KEY')
|
||||
|
||||
|
||||
# loading the embedding model
|
||||
@@ -91,6 +98,56 @@ def load_document(document_path):
|
||||
else:
|
||||
raise ValueError(f"Unsupported document type for {document_path}")
|
||||
|
||||
# Function to encode the image
|
||||
def encode_image(image_path):
|
||||
with open(image_path, "rb") as image_file:
|
||||
return base64.b64encode(image_file.read()).decode('utf-8')
|
||||
|
||||
# Vision API to process the image
|
||||
def process_image(image_path):
|
||||
global api_key
|
||||
|
||||
# Getting the base64 string
|
||||
base64_image = encode_image(image_path)
|
||||
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {api_key}"
|
||||
}
|
||||
|
||||
try:
|
||||
payload = {
|
||||
"model": "gpt-4o-mini",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": "What’s in this image?"
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": f"data:image/jpeg;base64,{base64_image}"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"max_tokens": 300
|
||||
}
|
||||
|
||||
response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
|
||||
# returning the content of the response
|
||||
response = response.json()['choices'][0]['message']['content']
|
||||
except Exception as e:
|
||||
response = "Image not good enough for processing"
|
||||
|
||||
return response
|
||||
|
||||
|
||||
# create image document
|
||||
def create_image_document(image_path):
|
||||
# getting the image name from the image path
|
||||
image_name = image_path.split('/')[-1].split('.')[0]
|
||||
@@ -100,9 +157,19 @@ def create_image_document(image_path):
|
||||
text = text_extractor.read_text_from_image(image_path)
|
||||
# removing special characters and line breaks
|
||||
text = ''.join(e for e in text if e.isalnum() or e.isspace() or e == '\n')
|
||||
doc = Document(page_content=text, metadata=metadata)
|
||||
# returning the document in a list
|
||||
return [doc]
|
||||
|
||||
# if the text is empty, then we will process the image with OpenAI vision model
|
||||
if text == '':
|
||||
text = process_image(image_path)
|
||||
|
||||
# checking if there's no value error or something, we will only return the text if there isnt any error
|
||||
if text != "Image not good enough for processing":
|
||||
# creating a document from the text
|
||||
doc = Document(page_content=text, metadata=metadata)
|
||||
# returning the document
|
||||
return [doc]
|
||||
else:
|
||||
pass # if there's an error, we will return None
|
||||
|
||||
|
||||
def save_embedded_data(embeddings, key="data"):
|
||||
|
||||
+95
-57
@@ -11,17 +11,93 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from text_extractor import TextExtractor\n",
|
||||
"from langchain_core.documents import Document"
|
||||
"from langchain_core.documents import Document\n",
|
||||
"import os\n",
|
||||
"import base64\n",
|
||||
"import requests\n",
|
||||
"from dotenv import load_dotenv\n",
|
||||
"load_dotenv()\n",
|
||||
"\n",
|
||||
"# OpenAI API Key\n",
|
||||
"api_key = os.getenv('OPENAI_API_KEY')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Vision Model Set Up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Function to encode the image\n",
|
||||
"def encode_image(image_path):\n",
|
||||
" with open(image_path, \"rb\") as image_file:\n",
|
||||
" return base64.b64encode(image_file.read()).decode('utf-8')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def process_image(image_path):\n",
|
||||
" global api_key\n",
|
||||
"\n",
|
||||
" # Getting the base64 string\n",
|
||||
" base64_image = encode_image(image_path)\n",
|
||||
"\n",
|
||||
" headers = {\n",
|
||||
" \"Content-Type\": \"application/json\",\n",
|
||||
" \"Authorization\": f\"Bearer {api_key}\"\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" try:\n",
|
||||
" payload = {\n",
|
||||
" \"model\": \"gpt-4o-mini\",\n",
|
||||
" \"messages\": [\n",
|
||||
" {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": [\n",
|
||||
" {\n",
|
||||
" \"type\": \"text\",\n",
|
||||
" \"text\": \"What’s in this image?\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {\n",
|
||||
" \"url\": f\"data:image/jpeg;base64,{base64_image}\"\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" ]\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" \"max_tokens\": 300\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" response = requests.post(\"https://api.openai.com/v1/chat/completions\", headers=headers, json=payload)\n",
|
||||
" # returning the content of the response\n",
|
||||
" response = response.json()['choices'][0]['message']['content']\n",
|
||||
" except Exception as e:\n",
|
||||
" response = \"Image not good enough for processing\"\n",
|
||||
"\n",
|
||||
" return response"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -35,79 +111,41 @@
|
||||
" text = text_extractor.read_text_from_image(image_path)\n",
|
||||
" # removing special characters and line breaks\n",
|
||||
" text = ''.join(e for e in text if e.isalnum() or e.isspace() or e == '\\n')\n",
|
||||
" doc = Document(page_content=text, metadata=metadata)\n",
|
||||
" # returning the document\n",
|
||||
" return [doc]"
|
||||
" \n",
|
||||
" # if the text is empty, then we will process the image with OpenAI vision model\n",
|
||||
" if text == '':\n",
|
||||
" text = process_image(image_path)\n",
|
||||
" \n",
|
||||
" # checking if there's no value error or something, we will only return the text if there isnt any error\n",
|
||||
" if text != \"Image not good enough for processing\":\n",
|
||||
" # creating a document from the text\n",
|
||||
" doc = Document(page_content=text, metadata=metadata)\n",
|
||||
" # returning the document\n",
|
||||
" return [doc]\n",
|
||||
" else:\n",
|
||||
" pass # if there's an error, we will return None"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[Document(metadata={'filename': 'IMG_1438'}, page_content='ex a\\n\\nAccidented car before repair\\n')]\n"
|
||||
"[Document(metadata={'filename': 'hyundai-sonata-auto-body-repair-before'}, page_content=\"The image shows a dark-colored car with visible damage on the driver's side. The damage appears to be a dent and scratches on the door and fender area. The car is parked indoors, likely in a garage.\")]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# testing the function\n",
|
||||
"image_path = 'data/IMG_1438.jpeg'\n",
|
||||
"image_path = 'data/hyundai-sonata-auto-body-repair-before.jpg'\n",
|
||||
"text = create_image_document(image_path)\n",
|
||||
"print(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'filename': 'IMG_1438'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"text[0].metadata"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
|
||||
@@ -80,3 +80,16 @@
|
||||
2024-08-08 14:29:17,820 - INFO - Search completed
|
||||
2024-08-08 14:29:17,820 - INFO - Page content: Accidented car Before repair
|
||||
|
||||
2024-08-08 21:55:11,668 - INFO - Loading the embeddings
|
||||
2024-08-08 21:55:11,669 - INFO - Load pretrained SentenceTransformer: BAAI/bge-small-en
|
||||
2024-08-08 21:55:15,477 - INFO - Embeddings loaded
|
||||
2024-08-08 21:55:15,477 - INFO - Loading data from ./data
|
||||
2024-08-08 21:56:51,671 - INFO - Data loaded
|
||||
2024-08-08 21:56:51,671 - INFO - Creating vector store
|
||||
2024-08-08 21:57:02,306 - INFO - Vector store created
|
||||
2024-08-08 21:57:02,306 - INFO - Saving the vector store
|
||||
2024-08-08 21:57:02,316 - INFO - Vector store saved
|
||||
2024-08-08 21:58:02,266 - INFO - Receiving the search query
|
||||
2024-08-08 21:58:08,023 - INFO - Searching for scratches on the door and fender area
|
||||
2024-08-08 21:58:08,277 - INFO - Search completed
|
||||
2024-08-08 21:58:08,277 - INFO - Page content: The image shows the front end of a car that has sustained damage. The bumper appears to be misaligned and there are visible signs of a collision, with dents and scratches on the bodywork. Parts like the grille and headlights also seem affected, indicating that the vehicle may require repairs.
|
||||
|
||||
@@ -14,3 +14,5 @@ docx
|
||||
fastapi[standard]
|
||||
pdfplumber
|
||||
pytesseract
|
||||
groq
|
||||
python-dotenv
|
||||
Binary file not shown.
Binary file not shown.
Reference in New Issue
Block a user