langchain/docs/modules/utils/combine_docs_examples/embeddings.ipynb

Embeddings

This notebook goes over how to use the Embedding class in LangChain.

The Embedding class is a class designed for interfacing with embeddings. There are lots of Embedding providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.

Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.

The base Embedding class in LangChain exposes two methods: embed_documents and embed_query. The largest difference is that these two methods have different interfaces: one works over multiple documents, while the other works over a single document. Besides this, another reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself).

OpenAI

Let's load the OpenAI Embedding class.

In [1]:

from langchain.embeddings import OpenAIEmbeddings

In [2]:

embeddings = OpenAIEmbeddings()

In [3]:

text = "This is a test document."

In [4]:

query_result = embeddings.embed_query(text)

In [5]:

doc_result = embeddings.embed_documents([text])

Cohere

Let's load the Cohere Embedding class.

In [1]:

from langchain.embeddings import CohereEmbeddings

In [2]:

embeddings = CohereEmbeddings(cohere_api_key= cohere_api_key)

In [3]:

text = "This is a test document."

In [4]:

query_result = embeddings.embed_query(text)

In [5]:

doc_result = embeddings.embed_documents([text])

Hugging Face Hub

Let's load the Hugging Face Embedding class.

In [7]:

from langchain.embeddings import HuggingFaceEmbeddings

In [16]:

embeddings = HuggingFaceEmbeddings()

In [12]:

text = "This is a test document."

In [13]:

query_result = embeddings.embed_query(text)

In [14]:

doc_result = embeddings.embed_documents([text])

TensorflowHub

Let's load the TensorflowHub Embedding class.

In [1]:

from langchain.embeddings import TensorflowHubEmbeddings

In [5]:

embeddings = TensorflowHubEmbeddings()

2023-01-30 23:53:01.652176: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-01-30 23:53:34.362802: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.

In [6]:

text = "This is a test document."

In [7]:

query_result = embeddings.embed_query(text)

InstructEmbeddings

Let's load the HuggingFace instruct Embeddings class.

In [8]:

from langchain.embeddings import HuggingFaceInstructEmbeddings

In [9]:

embeddings = HuggingFaceInstructEmbeddings(query_instruction="Represent the query for retrieval: ")

load INSTRUCTOR_Transformer
max_seq_length  512

In [10]:

text = "This is a test document."

In [11]:

query_result = embeddings.embed_query(text)

In [ ]: