2 changed files with 668 additions and 0 deletions
@ -0,0 +1,433 @@ |
|||||||
|
{ |
||||||
|
"cells": [ |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "05432987-80bc-4aa5-8c05-277861e19307", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"## Adds docstrings/comments to code and generates code summary" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "e706f175-1e83-4d2c-8613-056b2e532624", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"### Model Usage \n", |
||||||
|
"\n", |
||||||
|
"- **Open Source Models:**\n", |
||||||
|
"\n", |
||||||
|
" - Deployed via Endpoint: Hosted on a server and accessed remotely (Qwen 1.5-7)\n", |
||||||
|
" - Run Locally on Machine: Executed directly on a local device (Ollama running Llama 3.2-1B)\n", |
||||||
|
"\n", |
||||||
|
"- **Closed Source Models:** \n", |
||||||
|
" - Accessed through API key authentication: (OpenAI, Anthropic). \n" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "9ed667df-6660-4ba3-80c5-4c1c8f7e63f3", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# imports\n", |
||||||
|
"\n", |
||||||
|
"import os\n", |
||||||
|
"import io\n", |
||||||
|
"import sys \n", |
||||||
|
"import json\n", |
||||||
|
"import requests\n", |
||||||
|
"from dotenv import load_dotenv\n", |
||||||
|
"from openai import OpenAI\n", |
||||||
|
"import google.generativeai\n", |
||||||
|
"import anthropic\n", |
||||||
|
"import ollama\n", |
||||||
|
"from IPython.display import Markdown, display, update_display\n", |
||||||
|
"import gradio as gr\n", |
||||||
|
"from huggingface_hub import login, InferenceClient\n", |
||||||
|
"from transformers import AutoTokenizer, pipeline" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "c9dd4bf1-48cf-44dc-9d04-0ec6e8189a3c", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# environment\n", |
||||||
|
"\n", |
||||||
|
"load_dotenv()\n", |
||||||
|
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')\n", |
||||||
|
"os.environ['ANTHROPIC_API_KEY'] = os.getenv('ANTHROPIC_API_KEY')\n", |
||||||
|
"CODE_QWEN_URL = os.environ['CODE_QWEN_URL'] \n", |
||||||
|
"BIGBIRD_PEGASUS_URL = os.environ['BIGBIRD_PEGASUS_URL']\n", |
||||||
|
"HF_TOKEN = os.environ['HF_TOKEN']" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "71f671d6-50a7-43cf-9e04-52a159d67dab", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"!ollama pull llama3.2:1b" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "8e6f8f35-477d-4014-8fe9-874b5aee0061", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"openai = OpenAI()\n", |
||||||
|
"claude = anthropic.Anthropic()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "ae34b79c-425a-4f04-821a-8f1d9868b146", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"OPENAI_MODEL = \"gpt-4o-mini\"\n", |
||||||
|
"CLAUDE_MODEL = \"claude-3-haiku-20240307\"\n", |
||||||
|
"LLAMA_MODEL = \"llama3.2:1b\"" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "80e6d920-3c94-48c4-afd8-518f415ab777", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"code_qwen = \"Qwen/CodeQwen1.5-7B-Chat\"\n", |
||||||
|
"bigbird_pegasus = \"google/bigbird-pegasus-large-arxiv\"\n", |
||||||
|
"login(HF_TOKEN, add_to_git_credential=True)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "314cd8e3-2c10-4149-9818-4e6b0c05b871", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Uses Llama to Check Which Language the Code is Written In\n", |
||||||
|
"system_message_comments = \"You are an assistant designed to add docstrings and helpful comments to code for documentation purposes.\"\n", |
||||||
|
"system_message_comments += \"Respond back with properly formatted code, including docstrings and comments. Keep comments concise. \"\n", |
||||||
|
"system_message_comments += \"Do not respond with greetings, or any such extra output\"" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "66fa09e4-1b79-4f53-9bb7-904d515b2f26", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"system_message_summary = \"You are an assistant designed to summarise code for documentation purposes. You are not to display code again.\"\n", |
||||||
|
"system_message_summary += \"Respond back with a properly crafted summary, mentioning key details regarding to the code, such as workflow, code language.\"\n", |
||||||
|
"system_message_summary += \"Do not respond with greetings, or any such extra output. Do not respond in Markdown. Be thorough, keep explanation level at undergraduate level.\"" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "ea405820-f9d1-4cf1-b465-9ae5cd9016f6", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def user_prompt_for(code):\n", |
||||||
|
" user_prompt = \"Rewrite this code to include helpful comments and docstrings. \"\n", |
||||||
|
" user_prompt += \"Respond only with code.\\n\"\n", |
||||||
|
" user_prompt += code\n", |
||||||
|
" return user_prompt" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "26c9be56-1d4f-43e5-9bc4-eb5b76da8071", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def user_prompt_for_summary(code):\n", |
||||||
|
" user_prompt = \"Return the summary of the code.\\n\"\n", |
||||||
|
" user_prompt += code\n", |
||||||
|
" return user_prompt" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "c0ac22cb-dc96-4ae1-b00d-2747572f6945", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def messages_for(code):\n", |
||||||
|
" messages = [\n", |
||||||
|
" {\"role\": \"system\", \"content\": system_message_comments},\n", |
||||||
|
" {\"role\":\"user\", \"content\" : user_prompt_for(code)}\n", |
||||||
|
" ]\n", |
||||||
|
" return messages" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "eae1a8b4-68a8-4cd5-849e-0ecabd166a0c", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def messages_for_summary(code):\n", |
||||||
|
" messages = [\n", |
||||||
|
" {\"role\": \"system\", \"content\": system_message_summary},\n", |
||||||
|
" {\"role\":\"user\", \"content\" : user_prompt_for_summary(code)}\n", |
||||||
|
" ]\n", |
||||||
|
" return messages" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "5eb726dd-e09e-4011-8eb6-4d20f2830ff5", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"func = \"\"\"\n", |
||||||
|
"import time\n", |
||||||
|
"\n", |
||||||
|
"def calculate(iterations, param1, param2):\n", |
||||||
|
" result = 1.0\n", |
||||||
|
" for i in range(1, iterations+1):\n", |
||||||
|
" j = i * param1 - param2\n", |
||||||
|
" result -= (1/j)\n", |
||||||
|
" j = i * param1 + param2\n", |
||||||
|
" result += (1/j)\n", |
||||||
|
" return result\n", |
||||||
|
"\n", |
||||||
|
"start_time = time.time()\n", |
||||||
|
"result = calculate(100_000_000, 4, 1) * 4\n", |
||||||
|
"end_time = time.time()\n", |
||||||
|
"\n", |
||||||
|
"print(f\"Result: {result:.12f}\")\n", |
||||||
|
"print(f\"Execution Time: {(end_time - start_time):.6f} seconds\")\n", |
||||||
|
"\"\"\"" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "f61943b2-c939-4910-a670-58abaf464bb6", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def call_llama(code):\n", |
||||||
|
" # commented code\n", |
||||||
|
" messages = messages_for(code)\n", |
||||||
|
" response1 = ollama.chat(model=LLAMA_MODEL, messages=messages)\n", |
||||||
|
"\n", |
||||||
|
" # summary\n", |
||||||
|
" messages = messages_for_summary(code)\n", |
||||||
|
" response2 = ollama.chat(model=LLAMA_MODEL, messages=messages)\n", |
||||||
|
" \n", |
||||||
|
" return response1['message']['content'],response2['message']['content']" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "696fb97e-807e-40ed-b0e1-beb82d1108a6", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def call_claude(code):\n", |
||||||
|
" # commented code\n", |
||||||
|
" message1 = claude.messages.create(\n", |
||||||
|
" model=CLAUDE_MODEL,\n", |
||||||
|
" system=system_message_comments,\n", |
||||||
|
" messages=([{\"role\": \"user\", \"content\":user_prompt_for(code)}]),\n", |
||||||
|
" max_tokens=500\n", |
||||||
|
" )\n", |
||||||
|
"\n", |
||||||
|
" # summary\n", |
||||||
|
" message2 = claude.messages.create(\n", |
||||||
|
" model=CLAUDE_MODEL,\n", |
||||||
|
" system=system_message_summary,\n", |
||||||
|
" messages=([{\"role\": \"user\", \"content\":user_prompt_for_summary(code)}]),\n", |
||||||
|
" max_tokens=500\n", |
||||||
|
" )\n", |
||||||
|
" \n", |
||||||
|
" return message1.content[0].text,message2.content[0].text" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "4bf1db64-86fa-42a1-98dd-3df74607f8db", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def call_gpt(code):\n", |
||||||
|
" # commented code\n", |
||||||
|
" completion1 = openai.chat.completions.create(\n", |
||||||
|
" model=OPENAI_MODEL,\n", |
||||||
|
" messages=messages_for(code),\n", |
||||||
|
" )\n", |
||||||
|
"\n", |
||||||
|
" #summary\n", |
||||||
|
" completion2 = openai.chat.completions.create(\n", |
||||||
|
" model=OPENAI_MODEL,\n", |
||||||
|
" messages=messages_for_summary(code),\n", |
||||||
|
" )\n", |
||||||
|
" \n", |
||||||
|
" return completion1.choices[0].message.content,completion2.choices[0].message.content" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "6863dc42-cbcd-4a95-8b0a-cfbcbfed0764", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def call_codeqwen(code):\n", |
||||||
|
" # commented code\n", |
||||||
|
" tokenizer = AutoTokenizer.from_pretrained(code_qwen)\n", |
||||||
|
" messages = messages_for(code)\n", |
||||||
|
" text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\n", |
||||||
|
" client = InferenceClient(CODE_QWEN_URL, token=HF_TOKEN)\n", |
||||||
|
" response1 = client.text_generation(text, details=True, max_new_tokens=1000)\n", |
||||||
|
"\n", |
||||||
|
" # summary\n", |
||||||
|
" tokenizer = AutoTokenizer.from_pretrained(code_qwen)\n", |
||||||
|
" messages = messages_for_summary(code)\n", |
||||||
|
" text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\n", |
||||||
|
" client = InferenceClient(CODE_QWEN_URL, token=HF_TOKEN)\n", |
||||||
|
" response2 = client.text_generation(text, details=True, max_new_tokens=1000)\n", |
||||||
|
" \n", |
||||||
|
" return response1.generated_text ,response2.generated_text " |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "06d05c02-45e4-47da-b70b-cf433dfaca4c", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def create_docs(code,model):\n", |
||||||
|
" if model == \"Llama\":\n", |
||||||
|
" comments,summary = call_llama(code)\n", |
||||||
|
" elif model == \"Claude\":\n", |
||||||
|
" comments,summary = call_claude(code)\n", |
||||||
|
" elif model == \"GPT\":\n", |
||||||
|
" comments,summary = call_gpt(code)\n", |
||||||
|
" elif model == \"CodeQwen\":\n", |
||||||
|
" comments,summary = call_codeqwen(code)\n", |
||||||
|
" else:\n", |
||||||
|
" raise ValueError(\"Unknown Model\")\n", |
||||||
|
" return comments,summary" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "1b4ea289-5da9-4b0e-b4d4-f8f01e466839", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"css = \"\"\"\n", |
||||||
|
".comments {background-color: #00599C;}\n", |
||||||
|
".summary {background-color: #008B8B;}\n", |
||||||
|
"\"\"\"" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "89ad7c7b-b881-45d3-aadc-d7206af578fb", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"with gr.Blocks(css=css) as ui:\n", |
||||||
|
" gr.Markdown(\"### Code Documentation and Formatting\")\n", |
||||||
|
" with gr.Row():\n", |
||||||
|
" code = gr.Textbox(label=\"Input Code: \", value=func, lines=10)\n", |
||||||
|
" with gr.Row():\n", |
||||||
|
" model = gr.Dropdown([\"GPT\",\"Claude\",\"Llama\",\"CodeQwen\"],label=\"Select model\",value=\"GPT\")\n", |
||||||
|
" with gr.Row():\n", |
||||||
|
" docs = gr.Button(\"Add Comments and Sumarise Code\")\n", |
||||||
|
" with gr.Row():\n", |
||||||
|
" commented_code = gr.Textbox(label= \"Formatted Code\", lines=10,elem_classes=[\"comments\"])\n", |
||||||
|
" code_summary = gr.Textbox(label = \"Code Summary\", lines=10,elem_classes=[\"summary\"])\n", |
||||||
|
" docs.click(create_docs,inputs=[code,model],outputs=[commented_code,code_summary])," |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "1a9e3b1c-bfe6-4b71-aac8-fa36a491c157", |
||||||
|
"metadata": { |
||||||
|
"scrolled": true |
||||||
|
}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"ui.launch(inbrowser=True)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "ac895aa9-e044-4598-b715-d96d1c158656", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "5a96877c-22b7-4ad5-b235-1cf8f8b200a1", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"print(call_llama(func))" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "f11de1a2-52c0-41c7-ad88-01ef5f8bc628", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [] |
||||||
|
} |
||||||
|
], |
||||||
|
"metadata": { |
||||||
|
"kernelspec": { |
||||||
|
"display_name": "Python 3 (ipykernel)", |
||||||
|
"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": "3.11.11" |
||||||
|
} |
||||||
|
}, |
||||||
|
"nbformat": 4, |
||||||
|
"nbformat_minor": 5 |
||||||
|
} |
@ -0,0 +1,235 @@ |
|||||||
|
{ |
||||||
|
"cells": [ |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "fad6ee3f-45b8-4ac3-aa39-4a44dac91994", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"## Creating Text Embeddings From a Text File\n", |
||||||
|
"- Loading data using TextLoader\n", |
||||||
|
"- Splitting into chunks using CharacterTextSplitter\n", |
||||||
|
"- Converting chunks into vector embeddings and creating a vectorstore\n", |
||||||
|
"- Retreiving, reducing dimensions to 2D and displaying text embeddings" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "33b79f0d-7bd5-4e82-9295-2cc5cfa9495b", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# imports\n", |
||||||
|
"\n", |
||||||
|
"import os\n", |
||||||
|
"from dotenv import load_dotenv" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "391d12b3-ea25-4c66-93ba-71ef7c590be3", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"from langchain.document_loaders import DirectoryLoader, TextLoader\n", |
||||||
|
"from langchain.text_splitter import CharacterTextSplitter\n", |
||||||
|
"from langchain.schema import Document\n", |
||||||
|
"from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n", |
||||||
|
"from langchain.embeddings import HuggingFaceEmbeddings\n", |
||||||
|
"from langchain_chroma import Chroma\n", |
||||||
|
"import numpy as np\n", |
||||||
|
"from sklearn.manifold import TSNE\n", |
||||||
|
"import plotly.graph_objects as go" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "365d4346-bcf7-48b3-be13-b492f1877fab", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"MODEL = \"gpt-4o-mini\"\n", |
||||||
|
"db_name = \"my_vector_db\"" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "93887c1e-fb5e-4f9a-95f6-91a284e49695", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"load_dotenv(override=True)\n", |
||||||
|
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "86289eb8-25d8-405f-b1bb-3d9d9fed8671", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"loader = TextLoader(\"data.txt\", encoding=\"utf-8\")\n", |
||||||
|
"data = loader.load()\n", |
||||||
|
"\n", |
||||||
|
"documents = []\n", |
||||||
|
"for text in data:\n", |
||||||
|
" documents.append(text)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "32320fff-2321-40ea-9b7d-294dc2dfba3a", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"text_splitter = CharacterTextSplitter(chunk_size=20, chunk_overlap=5)\n", |
||||||
|
"chunks = text_splitter.split_documents(documents)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "fce762a5-4c78-4102-ab55-f95ee0c97286", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"len(chunks)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "ddb5bc12-af30-476d-bbbb-f91a3ae8af2f", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"embeddings = OpenAIEmbeddings()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "75ba81ec-9178-4ce4-83e2-82f937c85902", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"if os.path.exists(db_name):\n", |
||||||
|
" Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "c3ca2632-a8b3-4e7e-8370-d91579d31c23", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n", |
||||||
|
"print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "0de67066-73f5-446f-9033-a00d45b0cdc1", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Get one vector and find how many dimensions it has\n", |
||||||
|
"\n", |
||||||
|
"collection = vectorstore._collection\n", |
||||||
|
"sample_embedding = collection.get(limit=1, include=[\"embeddings\"])[\"embeddings\"][0] # represents a single vector\n", |
||||||
|
"dimensions = len(sample_embedding)\n", |
||||||
|
"print(f\"The vectors have {dimensions:,} dimensions\")" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "e50d972c-d740-4f0a-8bc2-e55ebe462a41", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"sample_embedding" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "aa96105d-b882-48d9-b088-6aab5db7b1e9", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"result = collection.get(include=['embeddings','documents'])\n", |
||||||
|
"vectors = np.array(result['embeddings']) \n", |
||||||
|
"documents = result['documents']" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "213b4cf2-db0a-4610-8d8f-97607996ed17", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Reduce dimensionality to 2D using t-SNE\n", |
||||||
|
"tsne = TSNE(n_components=2,perplexity=5, random_state=42)\n", |
||||||
|
"reduced_vectors = tsne.fit_transform(vectors)\n", |
||||||
|
"\n", |
||||||
|
"# Create the 2D scatter plot\n", |
||||||
|
"fig = go.Figure(data=[go.Scatter(\n", |
||||||
|
" x=reduced_vectors[:, 0],\n", |
||||||
|
" y=reduced_vectors[:, 1],\n", |
||||||
|
" mode='markers',\n", |
||||||
|
" marker=dict(size=5, opacity=0.8),\n", |
||||||
|
" text=[f\"Text: {d[:200]}...\" for d in documents],\n", |
||||||
|
" hoverinfo='text'\n", |
||||||
|
")])\n", |
||||||
|
"\n", |
||||||
|
"fig.update_layout(\n", |
||||||
|
" title='2D Chroma Vector Store Visualization',\n", |
||||||
|
" scene=dict(xaxis_title='x',yaxis_title='y'),\n", |
||||||
|
" width=800,\n", |
||||||
|
" height=600,\n", |
||||||
|
" margin=dict(r=20, b=10, l=10, t=40)\n", |
||||||
|
")\n", |
||||||
|
"\n", |
||||||
|
"fig.show()\n" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "7d13aa60-da3e-4c61-af69-1ba9087e0181", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [] |
||||||
|
} |
||||||
|
], |
||||||
|
"metadata": { |
||||||
|
"kernelspec": { |
||||||
|
"display_name": "Python 3 (ipykernel)", |
||||||
|
"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": "3.11.11" |
||||||
|
} |
||||||
|
}, |
||||||
|
"nbformat": 4, |
||||||
|
"nbformat_minor": 5 |
||||||
|
} |
Loading…
Reference in new issue