mirror of
https://github.com/arc53/DocsGPT.git
synced 2025-11-29 16:43:16 +00:00
1c734727a1
Transforms all rst files in provided folder to txt format first (utilising sphinx library). In my tests size of raw sample decreased 2-3 times.
39 lines
1.1 KiB
Python
39 lines
1.1 KiB
Python
from pathlib import Path
|
|
from langchain.text_splitter import CharacterTextSplitter
|
|
import faiss
|
|
from langchain.vectorstores import FAISS
|
|
from langchain.embeddings import OpenAIEmbeddings
|
|
import pickle
|
|
import dotenv
|
|
|
|
dotenv.load_dotenv()
|
|
|
|
|
|
# Here we load in the data in the format that Notion exports it in.
|
|
ps = list(Path("scikit-learn").glob("**/*.rst"))
|
|
# parse all child directories
|
|
|
|
data = []
|
|
sources = []
|
|
for p in ps:
|
|
with open(p) as f:
|
|
data.append(f.read())
|
|
sources.append(p)
|
|
|
|
# Here we split the documents, as needed, into smaller chunks.
|
|
# We do this due to the context limits of the LLMs.
|
|
text_splitter = CharacterTextSplitter(chunk_size=1500, separator="\n")
|
|
docs = []
|
|
metadatas = []
|
|
for i, d in enumerate(data):
|
|
splits = text_splitter.split_text(d)
|
|
docs.extend(splits)
|
|
metadatas.extend([{"source": sources[i]}] * len(splits))
|
|
|
|
|
|
# Here we create a vector store from the documents and save it to disk.
|
|
store = FAISS.from_texts(docs, OpenAIEmbeddings(), metadatas=metadatas)
|
|
faiss.write_index(store.index, "docs.index")
|
|
store.index = None
|
|
with open("faiss_store.pkl", "wb") as f:
|
|
pickle.dump(store, f) |