diff --git a/.gitignore b/.gitignore index e6214757..80495a6e 100644 --- a/.gitignore +++ b/.gitignore @@ -165,3 +165,5 @@ cython_debug/ # Database db + +.vscode \ No newline at end of file diff --git a/README.md b/README.md index 9e767c8d..9663021a 100644 --- a/README.md +++ b/README.md @@ -1,9 +1,9 @@ # embedchain [![](https://dcbadge.vercel.app/api/server/nhvCbCtKV?style=flat)](https://discord.gg/nhvCbCtKV) -![PyPI](https://img.shields.io/pypi/v/embedchain) +[![PyPI](https://img.shields.io/pypi/v/embedchain)](https://pypi.org/project/embedchain/) -embedchain is a framework to easily create LLM powered bots over any dataset. +embedchain is a framework to easily create LLM powered bots over any dataset. If you want a javascript version, check out [embedchain-js](https://github.com/embedchain/embedchainjs) It abstracts the entire process of loading a dataset, chunking it, creating embeddings and then storing in a vector database. diff --git a/embedchain/loaders/pdf_file.py b/embedchain/loaders/pdf_file.py index 2fec2f87..14b096c5 100644 --- a/embedchain/loaders/pdf_file.py +++ b/embedchain/loaders/pdf_file.py @@ -4,7 +4,7 @@ from embedchain.utils import clean_string class PdfFileLoader: - + def load_data(self, url): loader = PyPDFLoader(url) output = [] @@ -20,4 +20,4 @@ class PdfFileLoader: "content": content, "meta_data": meta_data, }) - return output \ No newline at end of file + return output