GPT4All
GPT4All is a free-to-use, locally running, privacy-aware chatbot. There is no GPU or internet required. It features popular models and its own models such as GPT4All Falcon, Wizard, etc.
This notebook explains how to useGPT4All embeddings with LangChain.
Install GPT4All's Python Bindings
%pip install--upgrade--quiet gpt4all>/dev/null
Note: you may need to restart the kernel to use updated packages.
from langchain_community.embeddingsimport GPT4AllEmbeddings
API Reference:GPT4AllEmbeddings
gpt4all_embd= GPT4AllEmbeddings()
100%|████████████████████████| 45.5M/45.5M [00:02<00:00, 18.5MiB/s]
``````output
Model downloaded at: /Users/rlm/.cache/gpt4all/ggml-all-MiniLM-L6-v2-f16.bin
``````output
objc[45711]: Class GGMLMetalClass is implemented in both /Users/rlm/anaconda3/envs/lcn2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libreplit-mainline-metal.dylib (0x29fe18208) and /Users/rlm/anaconda3/envs/lcn2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libllamamodel-mainline-metal.dylib (0x2a0244208). One of the two will be used. Which one is undefined.
text="This is a test document."
Embed the Textual Data
query_result= gpt4all_embd.embed_query(text)
With embed_documents you can embed multiple pieces of text. You can also map these embeddings withNomic's Atlas to see a visual representation of your data.
doc_result= gpt4all_embd.embed_documents([text])
Related
- Embedding modelconceptual guide
- Embedding modelhow-to guides