Spaces:
Runtime error
Runtime error
Download modules/embedder.py from ClearLove443/Robby-chatbot: direct link, hf CLI and curl.
- Browser
- Download file 2.79 kB
-
https://huggingface.co/spaces/ClearLove443/Robby-chatbot/resolve/main/modules/embedder.py
- Command line
-
hf download hf://spaces/ClearLove443/Robby-chatbot/modules/embedder.py
-
curl -L -o embedder.py https://huggingface.co/spaces/ClearLove443/Robby-chatbot/resolve/main/modules/embedder.py
2.79 kB
| import os | |
| import pickle | |
| import tempfile | |
| from langchain.document_loaders import PyPDFLoader, TextLoader | |
| from langchain.document_loaders.csv_loader import CSVLoader | |
| from langchain.embeddings.openai import OpenAIEmbeddings | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain.vectorstores import FAISS | |
| class Embedder: | |
| def __init__(self): | |
| self.PATH = "embeddings" | |
| self.createEmbeddingsDir() | |
| def createEmbeddingsDir(self): | |
| """ | |
| Creates a directory to store the embeddings vectors | |
| """ | |
| if not os.path.exists(self.PATH): | |
| os.mkdir(self.PATH) | |
| def storeDocEmbeds(self, file, original_filename): | |
| """ | |
| Stores document embeddings using Langchain and FAISS | |
| """ | |
| with tempfile.NamedTemporaryFile(mode="wb", delete=False) as tmp_file: | |
| tmp_file.write(file) | |
| tmp_file_path = tmp_file.name | |
| def get_file_extension(uploaded_file): | |
| file_extension = os.path.splitext(uploaded_file)[1].lower() | |
| return file_extension | |
| text_splitter = RecursiveCharacterTextSplitter( | |
| chunk_size=2000, | |
| chunk_overlap=100, | |
| length_function=len, | |
| ) | |
| file_extension = get_file_extension(original_filename) | |
| if file_extension == ".csv": | |
| loader = CSVLoader( | |
| file_path=tmp_file_path, | |
| encoding="utf-8", | |
| csv_args={ | |
| "delimiter": ",", | |
| }, | |
| ) | |
| data = loader.load() | |
| elif file_extension == ".pdf": | |
| loader = PyPDFLoader(file_path=tmp_file_path) | |
| data = loader.load_and_split(text_splitter) | |
| elif file_extension == ".txt": | |
| loader = TextLoader(file_path=tmp_file_path, encoding="utf-8") | |
| data = loader.load_and_split(text_splitter) | |
| # embeddings = OpenAIEmbeddings() | |
| from langchain.embeddings import HuggingFaceEmbeddings | |
| modelpath = "intfloat/e5-large-v2" | |
| embeddings = HuggingFaceEmbeddings(model_name=modelpath) | |
| vectors = FAISS.from_documents(data, embeddings) | |
| os.remove(tmp_file_path) | |
| # Save the vectors to a pickle file | |
| with open(f"{self.PATH}/{original_filename}.pkl", "wb") as f: | |
| pickle.dump(vectors, f) | |
| def getDocEmbeds(self, file, original_filename): | |
| """ | |
| Retrieves document embeddings | |
| """ | |
| if not os.path.isfile(f"{self.PATH}/{original_filename}.pkl"): | |
| self.storeDocEmbeds(file, original_filename) | |
| # Load the vectors from the pickle file | |
| with open(f"{self.PATH}/{original_filename}.pkl", "rb") as f: | |
| vectors = pickle.load(f) | |
| return vectors | |