1 changed files with 235 additions and 0 deletions
@ -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