Merge pull request PromtEngineer#75 from teleprint-me/issue-72-ingest…

…-device-options

Issue 72: Refactor document loading, add device selection, and update README

.gitignore

@@ -1,4 +1,164 @@
+# Ignore vscode
+/.vscode
 /DB
-/venv
-/.idea
-/__pycache__/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/

README.md

@@ -32,7 +32,19 @@ The current default file types are .txt, .pdf, .csv, and .xlsx, if you want to u
 Run the following command to ingest all the data.
 
 ```shell
-python ingest.py
+python ingest.py  # defaults to cuda
+```
+
+Use the device type argument to specify a given device.
+
+```sh
+python ingest.py --device_type cpu 
+```
+
+Use help for a full list of supported devices.
+
+```sh
+python ingest.py --help
 ```
 
 It will create an index containing the local vectorstore. Will take time, depending on the size of your documents.

constants.py

@@ -1,7 +1,16 @@
 import os
+
 # from dotenv import load_dotenv
 from chromadb.config import Settings
 
+# https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/excel.html?highlight=xlsx#microsoft-excel
+from langchain.document_loaders import (
+    CSVLoader,
+    PDFMinerLoader,
+    TextLoader,
+    UnstructuredExcelLoader,
+)
+
 # load_dotenv()
 ROOT_DIRECTORY = os.path.dirname(os.path.realpath(__file__))
 
@@ -15,4 +24,13 @@
         chroma_db_impl='duckdb+parquet',
         persist_directory=PERSIST_DIRECTORY,
         anonymized_telemetry=False
-)
+)
+
+# https://python.langchain.com/en/latest/_modules/langchain/document_loaders/excel.html#UnstructuredExcelLoader
+DOCUMENT_MAP = {
+    ".txt": TextLoader,
+    ".pdf": PDFMinerLoader,
+    ".csv": CSVLoader,
+    ".xls": UnstructuredExcelLoader,
+    ".xlxs": UnstructuredExcelLoader
+}

ingest.py

@@ -1,63 +1,70 @@
 import os
-import click
 from typing import List
-from utils import xlxs_to_csv
-from langchain.document_loaders import TextLoader, PDFMinerLoader, CSVLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import Chroma
+
+import click
 from langchain.docstore.document import Document
-from constants import CHROMA_SETTINGS, SOURCE_DIRECTORY, PERSIST_DIRECTORY
 from langchain.embeddings import HuggingFaceInstructEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+
+from constants import (CHROMA_SETTINGS, DOCUMENT_MAP, PERSIST_DIRECTORY,
+                       SOURCE_DIRECTORY)
 
 
 def load_single_document(file_path: str) -> Document:
     # Loads a single document from a file path
-    if file_path.endswith(".txt"):
-        loader = TextLoader(file_path, encoding="utf8")
-    elif file_path.endswith(".pdf"):
-        loader = PDFMinerLoader(file_path)
-    elif file_path.endswith(".csv"):
-        loader = CSVLoader(file_path)
+    file_extension = os.path.splitext(file_path)[1]
+    loader_class = DOCUMENT_MAP.get(file_extension)
+    if loader_class:
+        loader = loader_class(file_path)
+    else:
+        raise ValueError("Document type is undefined")
     return loader.load()[0]
 
 
 def load_documents(source_dir: str) -> List[Document]:
-    # Loads all documents from source documents directory
+    # Loads all documents from the source documents directory
     all_files = os.listdir(source_dir)
     docs = []
     for file_path in all_files:
-        if file_path[-4:] == 'xlsx':
-            for doc in xlxs_to_csv(f"{source_dir}/{file_path}"):
-                docs.append(load_single_document(doc))
-        elif file_path[-4:] in ['.txt', '.pdf', '.csv']:
-            docs.append(load_single_document(f"{source_dir}/{file_path}"))
+        file_extension = os.path.splitext(file_path)[1]
+        source_file_path = os.path.join(source_dir, file_path)
+        if file_extension in DOCUMENT_MAP.keys():
+            docs.append(load_single_document(source_file_path))
     return docs
-    # return [load_single_document(f"{source_dir}/{file_path}") for file_path in all_files if
-    #         file_path[-4:] in ['.txt', '.pdf', '.csv']]
-
-
-# @click.command()
-# @click.option('--device_type', default='gpu', help='device to run on, select gpu or cpu')
-# def main(device_type, ):
-#     # load the instructorEmbeddings
-#     if device_type in ['cpu', 'CPU']:
-#         device='cpu'
-#     else:
-#         device='cuda'
 
 
 @click.command()
-@click.option('--device_type', default='cuda', help='device to run on, select gpu, cpu or mps')
-def main(device_type, ):
-    # load the instructorEmbeddings
-    if device_type in ['cpu', 'CPU']:
-        device='cpu'
-    elif device_type in ['mps', 'MPS']:
-        device='mps'
-    else:
-        device='cuda'
-
-    #  Load documents and split in chunks
+@click.option(
+    "--device_type",
+    default="cuda",
+    type=click.Choice(
+        [
+            "cpu",
+            "cuda",
+            "ipu",
+            "xpu",
+            "mkldnn",
+            "opengl",
+            "opencl",
+            "ideep",
+            "hip",
+            "ve",
+            "fpga",
+            "ort",
+            "xla",
+            "lazy",
+            "vulkan",
+            "mps",
+            "meta",
+            "hpu",
+            "mtia",
+        ]
+    ),
+    help="Device to run on. (Default is cuda)",
+)
+def main(device_type):
+    # Load documents and split in chunks
     print(f"Loading documents from {SOURCE_DIRECTORY}")
     documents = load_documents(SOURCE_DIRECTORY)
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
@@ -66,10 +73,17 @@ def main(device_type, ):
     print(f"Split into {len(texts)} chunks of text")
 
     # Create embeddings
-    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl",
-                                               model_kwargs={"device": device})
+    embeddings = HuggingFaceInstructEmbeddings(
+        model_name="hkunlp/instructor-xl",
+        model_kwargs={"device": device_type},
+    )
 
-    db = Chroma.from_documents(texts, embeddings, persist_directory=PERSIST_DIRECTORY, client_settings=CHROMA_SETTINGS)
+    db = Chroma.from_documents(
+        texts,
+        embeddings,
+        persist_directory=PERSIST_DIRECTORY,
+        client_settings=CHROMA_SETTINGS,
+    )
     db.persist()
     db = None