change dataset name to new DB (#40)

* change dataset name to new DB

* add gitignore files

* remove commented code

* remove comments

.gitignore

@@ -1,3 +1,163 @@
+# 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/
 *.csv
 *.zip
 deeplake_store/

app.py

@@ -52,8 +52,6 @@ logging.basicConfig(level=logging.INFO)
 
 
 def log_likes(completion: Completion, like_data: gr.LikeData):
-    # make it a str so json-parsable
-
     collection = "liked_data-test"
 
     completion_json = completion.to_json(

cfg.py

@@ -23,13 +23,14 @@ ACTIVELOOP_TOKEN = os.getenv("ACTIVELOOP_TOKEN")
 if ACTIVELOOP_TOKEN is None:
     logger.warning("No activeloop token found, you will not be able to fetch data.")
 
-DEEPLAKE_DATASET = os.getenv("DEEPLAKE_DATASET", "ai-tutor-dataset_debug")
+DEEPLAKE_DATASET = os.getenv("DEEPLAKE_DATASET", "ai-tutor-dataset")
 DEEPLAKE_ORG = os.getenv("DEEPLAKE_ORG", "towards_ai")
 
 # if you want to use a local dataset, set the env. variable, it overrides all others
 DEEPLAKE_DATASET_PATH = os.getenv(
     "DEEPLAKE_DATASET_PATH", f"hub://{DEEPLAKE_ORG}/{DEEPLAKE_DATASET}"
 )
+
 logger.info(f"{DEEPLAKE_DATASET_PATH=}")
 
 example_questions = [

data/process_csvs_store.py

@@ -2,12 +2,8 @@ import pandas as pd
 import time
 import os
 from buster.documents_manager import DeepLakeDocumentsManager
-from deeplake.core.vectorstore import VectorStore
-from langchain.embeddings.openai import OpenAIEmbeddings
 
-# from openai import OpenAI
-
-DEEPLAKE_DATASET = os.getenv("DEEPLAKE_DATASET", "ai-tutor-dataset")
+DEEPLAKE_DATASET = os.getenv("DEEPLAKE_DATASET", "dataset-ai-tutor")
 DEEPLAKE_ORG = os.getenv("DEEPLAKE_ORG", "towards_ai")
 
 df1 = pd.read_csv("./data/llm_course.csv")
@@ -17,8 +13,9 @@ df4 = pd.read_csv("./data/filtered_tai_v2.csv")
 df5 = pd.read_csv("./data/wiki.csv")  # , encoding="ISO-8859-1")
 df6 = pd.read_csv("./data/openai.csv")
 df7 = pd.read_csv("./data/activeloop.csv")
+df8 = pd.read_csv("./data/langchain_docs.csv")
 
-print(len(df1), len(df2), len(df3), len(df4), len(df5), len(df6), len(df7))
+print(len(df1), len(df2), len(df3), len(df4), len(df5), len(df6), len(df7), len(df8))
 
 dataset_path = f"hub://{DEEPLAKE_ORG}/{DEEPLAKE_DATASET}"
 
@@ -98,35 +95,12 @@ dm.batch_add(
     csv_overwrite=False,
 )
 
-
-# client = OpenAI()
-
-# openai_embeddings = OpenAIEmbeddings()
-# def get_embedding(text, model="text-embedding-ada-002"):
-#     # Call to OpenAI's API to create the embedding
-#     response = client.embeddings.create(input=[text], model=model)
-
-#     # Extract the embedding data from the response
-#     embedding = response.data[0].embedding
-
-#     # Convert the ndarray to a list
-#     if isinstance(embedding, np.ndarray):
-#         embedding = embedding.tolist()
-
-#     return embedding
-
-
-# vs = VectorStore(
-#     dataset_path,
-#     runtime='compute_engine',
-#     token=os.environ['ACTIVELOOP_TOKEN']
-# )
-
-# data = vs.search(query = "select * where shape(embedding)[0] == 0")
-
-# vs.update_embedding(embedding_source_tensor = "text",
-#           query = "select * where shape(embedding)[0] == 0",
-#           exec_option = "compute_engine",
-#           embedding_function=get_embedding)
-
-# data2 = vs.search(query = "select * where shape(embedding)[0] == 0")
+dm.batch_add(
+    df=df8,
+    batch_size=3000,
+    min_time_interval=60,
+    num_workers=32,
+    csv_embeddings_filename="embeddings.csv",
+    csv_errors_filename="tmp.csv",
+    csv_overwrite=False,
+)