1d:I[11492,["/_next/static/chunks/ff3bf7cc534b7523.js","/_next/static/chunks/d7b1323b03251853.js","/_next/static/chunks/22b06a55bae91926.js","/_next/static/chunks/21aa533c6f3694f4.js"],"default"] 1e:T459,

Text to Vectors

Embeddings convert text into numerical vectors that capture semantic meaning.

How Embeddings Work

"cat"    → [0.2, 0.8, 0.1, ...]  (1536 dimensions)
"kitten" → [0.25, 0.75, 0.15, ...] ← Similar to "cat"!
"car"    → [0.9, 0.1, 0.7, ...]    ← Different from "cat"

Embedding Models in LangChain

# OpenAI (most popular)
from langchain_openai import OpenAIEmbeddings
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")

# Cohere
from langchain_cohere import CohereEmbeddings
embeddings = CohereEmbeddings()

# Local (HuggingFace)
from langchain_huggingface import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")

Using Embeddings

# Single text
vector = embeddings.embed_query("What is machine learning?")
print(len(vector))  # 1536 for OpenAI

# Multiple documents
vectors = embeddings.embed_documents([
    "Document 1 text",
    "Document 2 text"
])

1f:T4cd,

Storing and Searching Vectors

Popular Vector Stores

# Chroma (local, great for development)
from langchain_chroma import Chroma
vectorstore = Chroma.from_documents(docs, embeddings)

# FAISS (local, fast)
from langchain_community.vectorstores import FAISS
vectorstore = FAISS.from_documents(docs, embeddings)

# Pinecone (cloud, scalable)
from langchain_pinecone import PineconeVectorStore
vectorstore = PineconeVectorStore.from_documents(
    docs, embeddings, index_name="my-index"
)

Similarity Search

# Find similar documents
results = vectorstore.similarity_search(
    "What is machine learning?",
    k=4  # Return top 4 results
)

# With scores
results = vectorstore.similarity_search_with_score(
    "What is machine learning?",
    k=4
)
for doc, score in results:
    print(f"Score: {score}, Content: {doc.page_content[:100]}")

As Retriever

# Convert to retriever for use in chains
retriever = vectorstore.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 4}
)

# Use in chain
docs = retriever.invoke("What is ML?")

Understanding Embeddings

Understanding Embeddings

Text to Vectors

How Embeddings Work

Embedding Models in LangChain

Using Embeddings