├── .devcontainer
    └── devcontainer.json
├── .gitignore
├── .vscode
    └── extensions.json
├── README.md
├── app.py
├── docs
    ├── ds_llm_bq_91923.yml
    ├── ds_llm_bq_92023.yml
    ├── ds_llm_bq_92223.yml
    ├── ds_llm_sql_91923.yml
    └── ds_llm_sql_92023.yml
├── packages
    └── paths.py
├── requirements.txt
└── test_envs.py


/.devcontainer/devcontainer.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "Python 3",
 3 |   // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
 4 |   "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
 5 |   "customizations": {
 6 |     "codespaces": {
 7 |       "openFiles": [
 8 |         "README.md",
 9 |         "app.py"
10 |       ]
11 |     },
12 |     "vscode": {
13 |       "settings": {},
14 |       "extensions": [
15 |         "ms-python.python",
16 |         "ms-python.vscode-pylance"
17 |       ]
18 |     }
19 |   },
20 |   "updateContentCommand": "[ -f packages.txt ] && sudo apt update && sudo apt upgrade -y && sudo xargs apt install -y <packages.txt; [ -f requirements.txt ] && pip3 install --user -r requirements.txt; pip3 install --user streamlit; echo '✅ Packages installed and Requirements met'",
21 |   "postAttachCommand": {
22 |     "server": "streamlit run app.py --server.enableCORS false --server.enableXsrfProtection false"
23 |   },
24 |   "portsAttributes": {
25 |     "8501": {
26 |       "label": "Application",
27 |       "onAutoForward": "openPreview"
28 |     }
29 |   },
30 |   "forwardPorts": [
31 |     8501
32 |   ]
33 | }


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
  1 | # Byte-compiled / optimized / DLL files
  2 | __pycache__/
  3 | *.py[cod]
  4 | *$py.class
  5 | 
  6 | # C extensions
  7 | *.so
  8 | 
  9 | # Distribution / packaging
 10 | .Python
 11 | build/
 12 | develop-eggs/
 13 | dist/
 14 | downloads/
 15 | eggs/
 16 | .eggs/
 17 | lib/
 18 | lib64/
 19 | parts/
 20 | sdist/
 21 | var/
 22 | wheels/
 23 | share/python-wheels/
 24 | *.egg-info/
 25 | .installed.cfg
 26 | *.egg
 27 | MANIFEST
 28 | 
 29 | # PyInstaller
 30 | #  Usually these files are written by a python script from a template
 31 | #  before PyInstaller builds the exe, so as to inject date/other infos into it.
 32 | *.manifest
 33 | *.spec
 34 | 
 35 | # Installer logs
 36 | pip-log.txt
 37 | pip-delete-this-directory.txt
 38 | 
 39 | # Unit test / coverage reports
 40 | htmlcov/
 41 | .tox/
 42 | .nox/
 43 | .coverage
 44 | .coverage.*
 45 | .cache
 46 | nosetests.xml
 47 | coverage.xml
 48 | *.cover
 49 | *.py,cover
 50 | .hypothesis/
 51 | .pytest_cache/
 52 | cover/
 53 | 
 54 | # Translations
 55 | *.mo
 56 | *.pot
 57 | 
 58 | # Django stuff:
 59 | *.log
 60 | local_settings.py
 61 | db.sqlite3
 62 | db.sqlite3-journal
 63 | 
 64 | # Flask stuff:
 65 | instance/
 66 | .webassets-cache
 67 | 
 68 | # Scrapy stuff:
 69 | .scrapy
 70 | 
 71 | # Sphinx documentation
 72 | docs/_build/
 73 | 
 74 | # PyBuilder
 75 | .pybuilder/
 76 | target/
 77 | 
 78 | # Jupyter Notebook
 79 | .ipynb_checkpoints
 80 | 
 81 | # IPython
 82 | profile_default/
 83 | ipython_config.py
 84 | 
 85 | # pyenv
 86 | #   For a library or package, you might want to ignore these files since the code is
 87 | #   intended to run in multiple environments; otherwise, check them in:
 88 | # .python-version
 89 | 
 90 | # pipenv
 91 | #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 92 | #   However, in case of collaboration, if having platform-specific dependencies or dependencies
 93 | #   having no cross-platform support, pipenv may install dependencies that don't work, or not
 94 | #   install all needed dependencies.
 95 | #Pipfile.lock
 96 | 
 97 | # poetry
 98 | #   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
 99 | #   This is especially recommended for binary packages to ensure reproducibility, and is more
100 | #   commonly ignored for libraries.
101 | #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
102 | #poetry.lock
103 | 
104 | # pdm
105 | #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
106 | #pdm.lock
107 | #   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
108 | #   in version control.
109 | #   https://pdm.fming.dev/#use-with-ide
110 | .pdm.toml
111 | 
112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
113 | __pypackages__/
114 | 
115 | # Celery stuff
116 | celerybeat-schedule
117 | celerybeat.pid
118 | 
119 | # SageMath parsed files
120 | *.sage.py
121 | 
122 | # Environments
123 | .env
124 | .venv
125 | env/
126 | venv/
127 | ENV/
128 | env.bak/
129 | venv.bak/
130 | 
131 | # Spyder project settings
132 | .spyderproject
133 | .spyproject
134 | 
135 | # Rope project settings
136 | .ropeproject
137 | 
138 | # mkdocs documentation
139 | /site
140 | 
141 | # mypy
142 | .mypy_cache/
143 | .dmypy.json
144 | dmypy.json
145 | 
146 | # Pyre type checker
147 | .pyre/
148 | 
149 | # pytype static type analyzer
150 | .pytype/
151 | 
152 | # Cython debug symbols
153 | cython_debug/
154 | 
155 | # PyCharm
156 | #  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
157 | #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
158 | #  and can be added to the global gitignore or merged into this file.  For a more nuclear
159 | #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
160 | #.idea/
161 | 
162 | 
163 | credentials/
164 | .env
165 | LLM_BQ.ipynb
166 | LLM_SQL.ipynb


--------------------------------------------------------------------------------
/.vscode/extensions.json:
--------------------------------------------------------------------------------
1 | {
2 |     "recommendations": [
3 |         "github.codespaces"
4 |     ]
5 | }


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # Natural Language to SQL
  2 | ## Description
  3 | 
  4 | In this this repository you will find an application designed to serve as a Data Analytics Assistant. You can chat with it in natural language and the assistant will translate it to SQL queries emerging by [Chain of Thought](https://en.wikipedia.org/wiki/Prompt_engineering#Chain-of-thought), go to the db, execute the query and finally, answering your question in natural language. 
  5 | 
  6 | It enables users to interact with and analyze BigQuery and MySQL databases seamlessly. The application is built using LangChain(SQL Agents), Streamlit, SQL Alchemy and Google Cloud-BigQuery.
  7 | 
  8 | It intends to meet the demands of those who need more **general insights** from the data. 
  9 | 
 10 | - Some of those questions might be:
 11 | 
 12 | What are the top-performing products in the last quarter?
 13 | Which marketing channels have the highest customer acquisition cost?
 14 | How do sales promotions impact revenue?
 15 | 
 16 | 
 17 | Other concerns that could involve several joins and complex reasoning like **churn, retention, life-time value, seasonality by region**, etc might create hallucinations outcomming poor results in term of precision.  
 18 | 
 19 | ## Features 
 20 | - **Data Analytics Assistant** : A user-friendly interface to ask in natural langauge about data. 
 21 | - **Database Support** : Compatible with BigQuery and MySQL databases. 
 22 | - **Interactive UI** : Built with Streamlit for an interactive user experience.
 23 | ## Technologies Used 
 24 | - [LangChain](https://github.com/langchain-ai/langchain): Open source framework for building context-aware reasoning applications, enabling almost unlimited power by large language models.
 25 | - [Streamlit](https://streamlit.io/) : Free and open-source front-end framework to rapidly build and share beautiful machine learning and data science web apps. 
 26 | - [SQL Alchemy](https://github.com/sqlalchemy/sqlalchemy) : SQLAlchemy is a tool in Python that helps software developers work with databases more easily. It allows you to use Python code to run SQL queries and manage relationships between data, giving you the best of both worlds—Python's simplicity and SQL's capabilities.
 27 | 
 28 | 
 29 | 
 30 | ## How to Use
 31 | #### Step 1: Clone the Repository
 32 | 
 33 | ```bash
 34 | 
 35 | git clone https://github.com/cremerf/ds_llm_sql.git .
 36 | ```
 37 | #### Step 2: Create .env file with enviroment variables
 38 | 
 39 | ```toml
 40 | DB_USER=""
 41 | DB_PASSWORD=""
 42 | DB_HOST= ""
 43 | DB_NAME= ""
 44 | PROJECT_ID_GCP= ""
 45 | DATASET_BQ= ""
 46 | OPENAI_API_KEY=""
 47 | ```
 48 | Store this file in the root directory of the app
 49 | 
 50 | #### Step 2.1: Create credentials folder and save GCP keys
 51 | 
 52 | ###### Step 2.1.1: Open Google Cloud Console 
 53 | - Navigate to [Google Cloud Console](https://console.cloud.google.com/) .
 54 | ###### Step 2.1.2: Select Project
 55 | - Choose the project for which you want to create the service account.
 56 | ###### Step 2.1.3: Go to IAM & Admin
 57 | - In the left sidebar, click on "IAM & Admin" and then select "Service accounts."
 58 | ###### Step 2.1.4: Create Service Account
 59 | - Click on "Create Service Account."
 60 | - Fill in the required details like name, description, and click "Create."
 61 | ###### Step 2.1.5: Assign Roles
 62 | - Assign necessary roles to the service account and click "Continue."
 63 | ###### Step 2.1.6: Add Users (Optional)
 64 | - Add users who can access this service account, if needed. 
 65 | - Click "Done."
 66 | ###### Step 2.1.7: Generate Key
 67 | - In the Service accounts list, find the newly created service account.
 68 | - Click on the three-dot menu (actions) and select "Manage keys."
 69 | - Click on "Add Key" and choose "JSON."
 70 | ###### Step 2.1.8: Download Key
 71 | Download the JSON key and store it in the credentials/ folder
 72 | 
 73 | #### Step 3: Create running env and install requirements
 74 | 
 75 | ###### Step 3.1: Install Miniconda/Conda 
 76 | - Download Miniconda installer
 77 | 
 78 | ```bash
 79 | 
 80 | wget https://repo.anaconda.com/archive/Anaconda3-2021.05-Linux-x86_64.sh
 81 | ```
 82 | 
 83 | Install it in your home user
 84 | 
 85 | 
 86 | ###### Step 3.2: Create Environment 
 87 | - Create a new environment with Python 3.11:
 88 | 
 89 | ```bash
 90 | 
 91 | conda create --name ds_llm_analytics python=3.11
 92 | ```
 93 | 
 94 | ###### Step 3.3: Create Environment 
 95 | 
 96 | ```bash
 97 | 
 98 | pip install -r requirements.txt
 99 | ```
100 | 
101 | By default, the installed dependencies will only run with BigQuery databases. If you wish to interact with MySQL DB, create a conda env using this yml file: ds_llm_sql_92023.yml  
102 | 
103 | 
104 | ```bash
105 | 
106 | conda env create --file docs/ds_llm_sql_92023.yml
107 | ```
108 | 
109 | #### Step 4: Run the Streamlit Application
110 | 
111 | ```bash
112 | 
113 | streamlit run app.py
114 | ```
115 | 
116 | This will launch the Streamlit app in your default web browser. Follow the on-screen instructions to interact with BigQuery or MySQL databases.---
117 | 
118 | Feel free to fork this repository to better suit the actual content and functionality of your use case.
119 | 
120 | 
121 | 


--------------------------------------------------------------------------------
/app.py:
--------------------------------------------------------------------------------
 1 | 
 2 | # LangChain imports
 3 | from langchain.sql_database import SQLDatabase
 4 | from langchain.llms import OpenAI
 5 | from langchain.agents import AgentType, initialize_agent, load_tools
 6 | from langchain.chat_models import ChatOpenAI
 7 | from langchain.callbacks import StreamlitCallbackHandler
 8 | from langchain.agents import create_sql_agent
 9 | from langchain.agents.agent_toolkits import SQLDatabaseToolkit
10 | from dotenv import load_dotenv
11 | 
12 | # Streamlit
13 | import streamlit as st
14 | 
15 | # Built-in
16 | import os
17 | import json
18 | 
19 | # Dependency to query BQ-GCP
20 | import pyarrow
21 | 
22 | # Paths
23 | from packages.paths import DS_LLM_PATHS
24 | 
25 | PATHS = DS_LLM_PATHS()
26 | load_dotenv()
27 | 
28 | PROJECT_ID = os.environ.get("PROJECT_ID_GCP")
29 | DATASET_ID = os.environ.get("DATASET_BQ")
30 | OPENAI_KEY = os.environ.get("OPENAI_API_KEY")
31 | 
32 | 
33 | sqlalchemy_url = f'bigquery://{PROJECT_ID}/{DATASET_ID}?credentials_path={PATHS.GCP_KEYS}'
34 | 
35 | st.title("🤖 English to SQL - LangChain project")
36 | st.title("Chat with your BigQuery database!")
37 | st.subheader("This is cfGPT, your data analytics assistant.", divider='gray')
38 | st.subheader("Powered by :blue[cremerf]")
39 | api_key = st.text_input("OpenAI key", type='password')
40 | 
41 | 
42 | if api_key:
43 |     db = SQLDatabase.from_uri(sqlalchemy_url)
44 |     llm = ChatOpenAI(model='gpt-4', temperature=0, openai_api_key=api_key)
45 |     toolkit = SQLDatabaseToolkit(db=db, llm=llm)
46 |     agent_executor = create_sql_agent(
47 |         llm=llm,
48 |         toolkit=toolkit,
49 |         verbose=True,
50 |         agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
51 |     )
52 | else:
53 |     st.write("Please input OpenAI key")
54 | 
55 | if prompt := st.chat_input():
56 |     st.chat_message("user").write(prompt)
57 |     with st.chat_message("assistant"):
58 |         st_callback = StreamlitCallbackHandler(st.container())
59 |         response = agent_executor.run(prompt, callbacks=[st_callback])
60 |         
61 |         st.write(response)
62 | 


--------------------------------------------------------------------------------
/docs/ds_llm_bq_91923.yml:
--------------------------------------------------------------------------------
  1 | name: ds_llm_bq
  2 | channels:
  3 |   - conda-forge
  4 |   - defaults
  5 | dependencies:
  6 |   - _libgcc_mutex=0.1=main
  7 |   - _openmp_mutex=5.1=1_gnu
  8 |   - asttokens=2.4.0=pyhd8ed1ab_0
  9 |   - backcall=0.2.0=pyh9f0ad1d_0
 10 |   - backports=1.0=pyhd8ed1ab_3
 11 |   - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
 12 |   - bzip2=1.0.8=h7b6447c_0
 13 |   - ca-certificates=2023.7.22=hbcca054_0
 14 |   - comm=0.1.4=pyhd8ed1ab_0
 15 |   - debugpy=1.6.7=py311h6a678d5_0
 16 |   - decorator=5.1.1=pyhd8ed1ab_0
 17 |   - exceptiongroup=1.1.3=pyhd8ed1ab_0
 18 |   - executing=1.2.0=pyhd8ed1ab_0
 19 |   - importlib-metadata=6.8.0=pyha770c72_0
 20 |   - importlib_metadata=6.8.0=hd8ed1ab_0
 21 |   - ipykernel=6.25.2=pyh2140261_0
 22 |   - ipython=8.15.0=pyh0d859eb_0
 23 |   - jedi=0.19.0=pyhd8ed1ab_0
 24 |   - jupyter_client=8.3.1=pyhd8ed1ab_0
 25 |   - jupyter_core=5.3.1=py311h38be061_0
 26 |   - ld_impl_linux-64=2.38=h1181459_1
 27 |   - libffi=3.4.4=h6a678d5_0
 28 |   - libgcc-ng=11.2.0=h1234567_1
 29 |   - libgomp=11.2.0=h1234567_1
 30 |   - libsodium=1.0.18=h36c2ea0_1
 31 |   - libstdcxx-ng=11.2.0=h1234567_1
 32 |   - libuuid=1.41.5=h5eee18b_0
 33 |   - matplotlib-inline=0.1.6=pyhd8ed1ab_0
 34 |   - ncurses=6.4=h6a678d5_0
 35 |   - nest-asyncio=1.5.6=pyhd8ed1ab_0
 36 |   - openssl=3.0.10=h7f8727e_2
 37 |   - packaging=23.1=pyhd8ed1ab_0
 38 |   - parso=0.8.3=pyhd8ed1ab_0
 39 |   - pexpect=4.8.0=pyh1a96a4e_2
 40 |   - pickleshare=0.7.5=py_1003
 41 |   - pip=23.2.1=py311h06a4308_0
 42 |   - platformdirs=3.10.0=pyhd8ed1ab_0
 43 |   - prompt-toolkit=3.0.39=pyha770c72_0
 44 |   - prompt_toolkit=3.0.39=hd8ed1ab_0
 45 |   - psutil=5.9.0=py311h5eee18b_0
 46 |   - ptyprocess=0.7.0=pyhd3deb0d_0
 47 |   - pure_eval=0.2.2=pyhd8ed1ab_0
 48 |   - pygments=2.16.1=pyhd8ed1ab_0
 49 |   - python=3.11.5=h955ad1f_0
 50 |   - python-dateutil=2.8.2=pyhd8ed1ab_0
 51 |   - python_abi=3.11=2_cp311
 52 |   - pyzmq=25.1.0=py311h6a678d5_0
 53 |   - readline=8.2=h5eee18b_0
 54 |   - setuptools=68.0.0=py311h06a4308_0
 55 |   - six=1.16.0=pyh6c4a22f_0
 56 |   - sqlite=3.41.2=h5eee18b_0
 57 |   - stack_data=0.6.2=pyhd8ed1ab_0
 58 |   - tk=8.6.12=h1ccaba5_0
 59 |   - tornado=6.3.2=py311h5eee18b_0
 60 |   - traitlets=5.10.0=pyhd8ed1ab_0
 61 |   - typing-extensions=4.8.0=hd8ed1ab_0
 62 |   - typing_extensions=4.8.0=pyha770c72_0
 63 |   - wcwidth=0.2.6=pyhd8ed1ab_0
 64 |   - wheel=0.38.4=py311h06a4308_0
 65 |   - xz=5.4.2=h5eee18b_0
 66 |   - zeromq=4.3.4=h9c3ff4c_1
 67 |   - zipp=3.16.2=pyhd8ed1ab_0
 68 |   - zlib=1.2.13=h5eee18b_0
 69 |   - pip:
 70 |       - aiohttp==3.8.5
 71 |       - aiosignal==1.3.1
 72 |       - anyio==4.0.0
 73 |       - async-timeout==4.0.3
 74 |       - attrs==23.1.0
 75 |       - backoff==2.2.1
 76 |       - bcrypt==4.0.1
 77 |       - cachetools==5.3.1
 78 |       - certifi==2023.7.22
 79 |       - charset-normalizer==3.2.0
 80 |       - chroma-hnswlib==0.7.3
 81 |       - chromadb==0.4.11
 82 |       - click==8.1.7
 83 |       - coloredlogs==15.0.1
 84 |       - dataclasses-json==0.5.14
 85 |       - db-dtypes==1.1.1
 86 |       - fastapi==0.99.1
 87 |       - filelock==3.12.4
 88 |       - flatbuffers==23.5.26
 89 |       - frozenlist==1.4.0
 90 |       - fsspec==2023.9.1
 91 |       - google-api-core==2.11.1
 92 |       - google-auth==2.23.0
 93 |       - google-cloud-bigquery==3.11.4
 94 |       - google-cloud-bigquery-storage==2.22.0
 95 |       - google-cloud-core==2.3.3
 96 |       - google-crc32c==1.5.0
 97 |       - google-resumable-media==2.6.0
 98 |       - googleapis-common-protos==1.60.0
 99 |       - greenlet==2.0.2
100 |       - grpcio==1.58.0
101 |       - grpcio-status==1.58.0
102 |       - h11==0.14.0
103 |       - httptools==0.6.0
104 |       - huggingface-hub==0.16.4
105 |       - humanfriendly==10.0
106 |       - idna==3.4
107 |       - importlib-resources==6.0.1
108 |       - langchain==0.0.295
109 |       - langsmith==0.0.38
110 |       - marshmallow==3.20.1
111 |       - monotonic==1.6
112 |       - mpmath==1.3.0
113 |       - multidict==6.0.4
114 |       - mypy-extensions==1.0.0
115 |       - numexpr==2.8.6
116 |       - numpy==1.26.0
117 |       - onnxruntime==1.15.1
118 |       - openai==0.28.0
119 |       - overrides==7.4.0
120 |       - pandas==2.1.0
121 |       - posthog==3.0.2
122 |       - proto-plus==1.22.3
123 |       - protobuf==4.24.3
124 |       - pulsar-client==3.3.0
125 |       - pyarrow==13.0.0
126 |       - pyasn1==0.5.0
127 |       - pyasn1-modules==0.3.0
128 |       - pydantic==1.10.12
129 |       - pypika==0.48.9
130 |       - python-dotenv==1.0.0
131 |       - pytz==2023.3.post1
132 |       - pyyaml==6.0.1
133 |       - regex==2023.8.8
134 |       - requests==2.31.0
135 |       - rsa==4.9
136 |       - sniffio==1.3.0
137 |       - sqlalchemy==1.4.49
138 |       - sqlalchemy-bigquery==1.8.0
139 |       - starlette==0.27.0
140 |       - sympy==1.12
141 |       - tabulate==0.9.0
142 |       - tenacity==8.2.3
143 |       - tiktoken==0.5.1
144 |       - tokenizers==0.14.0
145 |       - tqdm==4.66.1
146 |       - typer==0.9.0
147 |       - typing-inspect==0.9.0
148 |       - tzdata==2023.3
149 |       - urllib3==1.26.16
150 |       - uvicorn==0.23.2
151 |       - uvloop==0.17.0
152 |       - watchfiles==0.20.0
153 |       - websockets==11.0.3
154 |       - yarl==1.9.2
155 | prefix: /home/fcremer29/miniconda3/envs/ds_llm_bq
156 | 


--------------------------------------------------------------------------------
/docs/ds_llm_bq_92023.yml:
--------------------------------------------------------------------------------
  1 | name: ds_llm_bq
  2 | channels:
  3 |   - conda-forge
  4 |   - defaults
  5 | dependencies:
  6 |   - _libgcc_mutex=0.1=main
  7 |   - _openmp_mutex=5.1=1_gnu
  8 |   - asttokens=2.4.0=pyhd8ed1ab_0
  9 |   - backcall=0.2.0=pyh9f0ad1d_0
 10 |   - backports=1.0=pyhd8ed1ab_3
 11 |   - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
 12 |   - bzip2=1.0.8=h7b6447c_0
 13 |   - ca-certificates=2023.7.22=hbcca054_0
 14 |   - comm=0.1.4=pyhd8ed1ab_0
 15 |   - debugpy=1.6.7=py311h6a678d5_0
 16 |   - decorator=5.1.1=pyhd8ed1ab_0
 17 |   - exceptiongroup=1.1.3=pyhd8ed1ab_0
 18 |   - executing=1.2.0=pyhd8ed1ab_0
 19 |   - importlib-metadata=6.8.0=pyha770c72_0
 20 |   - importlib_metadata=6.8.0=hd8ed1ab_0
 21 |   - ipykernel=6.25.2=pyh2140261_0
 22 |   - ipython=8.15.0=pyh0d859eb_0
 23 |   - jedi=0.19.0=pyhd8ed1ab_0
 24 |   - jupyter_client=8.3.1=pyhd8ed1ab_0
 25 |   - jupyter_core=5.3.1=py311h38be061_0
 26 |   - ld_impl_linux-64=2.38=h1181459_1
 27 |   - libffi=3.4.4=h6a678d5_0
 28 |   - libgcc-ng=11.2.0=h1234567_1
 29 |   - libgomp=11.2.0=h1234567_1
 30 |   - libsodium=1.0.18=h36c2ea0_1
 31 |   - libstdcxx-ng=11.2.0=h1234567_1
 32 |   - libuuid=1.41.5=h5eee18b_0
 33 |   - matplotlib-inline=0.1.6=pyhd8ed1ab_0
 34 |   - ncurses=6.4=h6a678d5_0
 35 |   - nest-asyncio=1.5.6=pyhd8ed1ab_0
 36 |   - openssl=3.0.10=h7f8727e_2
 37 |   - packaging=23.1=pyhd8ed1ab_0
 38 |   - parso=0.8.3=pyhd8ed1ab_0
 39 |   - pexpect=4.8.0=pyh1a96a4e_2
 40 |   - pickleshare=0.7.5=py_1003
 41 |   - pip=23.2.1=py311h06a4308_0
 42 |   - platformdirs=3.10.0=pyhd8ed1ab_0
 43 |   - prompt-toolkit=3.0.39=pyha770c72_0
 44 |   - prompt_toolkit=3.0.39=hd8ed1ab_0
 45 |   - psutil=5.9.0=py311h5eee18b_0
 46 |   - ptyprocess=0.7.0=pyhd3deb0d_0
 47 |   - pure_eval=0.2.2=pyhd8ed1ab_0
 48 |   - pygments=2.16.1=pyhd8ed1ab_0
 49 |   - python=3.11.5=h955ad1f_0
 50 |   - python-dateutil=2.8.2=pyhd8ed1ab_0
 51 |   - python_abi=3.11=2_cp311
 52 |   - pyzmq=25.1.0=py311h6a678d5_0
 53 |   - readline=8.2=h5eee18b_0
 54 |   - setuptools=68.0.0=py311h06a4308_0
 55 |   - six=1.16.0=pyh6c4a22f_0
 56 |   - sqlite=3.41.2=h5eee18b_0
 57 |   - stack_data=0.6.2=pyhd8ed1ab_0
 58 |   - tk=8.6.12=h1ccaba5_0
 59 |   - tornado=6.3.2=py311h5eee18b_0
 60 |   - traitlets=5.10.0=pyhd8ed1ab_0
 61 |   - typing-extensions=4.8.0=hd8ed1ab_0
 62 |   - typing_extensions=4.8.0=pyha770c72_0
 63 |   - wcwidth=0.2.6=pyhd8ed1ab_0
 64 |   - wheel=0.38.4=py311h06a4308_0
 65 |   - xz=5.4.2=h5eee18b_0
 66 |   - zeromq=4.3.4=h9c3ff4c_1
 67 |   - zipp=3.16.2=pyhd8ed1ab_0
 68 |   - zlib=1.2.13=h5eee18b_0
 69 |   - pip:
 70 |       - aiohttp==3.8.5
 71 |       - aiosignal==1.3.1
 72 |       - altair==5.1.1
 73 |       - anyio==4.0.0
 74 |       - async-timeout==4.0.3
 75 |       - attrs==23.1.0
 76 |       - backoff==2.2.1
 77 |       - bcrypt==4.0.1
 78 |       - blinker==1.6.2
 79 |       - cachetools==5.3.1
 80 |       - certifi==2023.7.22
 81 |       - charset-normalizer==3.2.0
 82 |       - chroma-hnswlib==0.7.3
 83 |       - chromadb==0.4.11
 84 |       - click==8.1.7
 85 |       - coloredlogs==15.0.1
 86 |       - dataclasses-json==0.5.14
 87 |       - db-dtypes==1.1.1
 88 |       - fastapi==0.99.1
 89 |       - filelock==3.12.4
 90 |       - flatbuffers==23.5.26
 91 |       - frozenlist==1.4.0
 92 |       - fsspec==2023.9.1
 93 |       - gitdb==4.0.10
 94 |       - gitpython==3.1.36
 95 |       - google-api-core==2.11.1
 96 |       - google-auth==2.23.0
 97 |       - google-cloud-bigquery==3.11.4
 98 |       - google-cloud-bigquery-storage==2.22.0
 99 |       - google-cloud-core==2.3.3
100 |       - google-crc32c==1.5.0
101 |       - google-resumable-media==2.6.0
102 |       - googleapis-common-protos==1.60.0
103 |       - greenlet==2.0.2
104 |       - grpcio==1.58.0
105 |       - grpcio-status==1.58.0
106 |       - h11==0.14.0
107 |       - httptools==0.6.0
108 |       - huggingface-hub==0.16.4
109 |       - humanfriendly==10.0
110 |       - idna==3.4
111 |       - importlib-resources==6.0.1
112 |       - jinja2==3.1.2
113 |       - jsonschema==4.19.1
114 |       - jsonschema-specifications==2023.7.1
115 |       - langchain==0.0.295
116 |       - langsmith==0.0.38
117 |       - markdown-it-py==3.0.0
118 |       - markupsafe==2.1.3
119 |       - marshmallow==3.20.1
120 |       - mdurl==0.1.2
121 |       - monotonic==1.6
122 |       - mpmath==1.3.0
123 |       - multidict==6.0.4
124 |       - mypy-extensions==1.0.0
125 |       - numexpr==2.8.6
126 |       - numpy==1.26.0
127 |       - onnxruntime==1.15.1
128 |       - openai==0.28.0
129 |       - overrides==7.4.0
130 |       - pandas==2.1.0
131 |       - pillow==9.5.0
132 |       - posthog==3.0.2
133 |       - proto-plus==1.22.3
134 |       - protobuf==4.24.3
135 |       - pulsar-client==3.3.0
136 |       - pyarrow==13.0.0
137 |       - pyasn1==0.5.0
138 |       - pyasn1-modules==0.3.0
139 |       - pydantic==1.10.12
140 |       - pydeck==0.8.0
141 |       - pympler==1.0.1
142 |       - pypika==0.48.9
143 |       - python-dotenv==1.0.0
144 |       - pytz==2023.3.post1
145 |       - pytz-deprecation-shim==0.1.0.post0
146 |       - pyyaml==6.0.1
147 |       - referencing==0.30.2
148 |       - regex==2023.8.8
149 |       - requests==2.31.0
150 |       - rich==13.5.3
151 |       - rpds-py==0.10.3
152 |       - rsa==4.9
153 |       - smmap==5.0.1
154 |       - sniffio==1.3.0
155 |       - sqlalchemy==1.4.49
156 |       - sqlalchemy-bigquery==1.8.0
157 |       - starlette==0.27.0
158 |       - streamlit==1.26.0
159 |       - sympy==1.12
160 |       - tabulate==0.9.0
161 |       - tenacity==8.2.3
162 |       - tiktoken==0.5.1
163 |       - tokenizers==0.14.0
164 |       - toml==0.10.2
165 |       - toolz==0.12.0
166 |       - tqdm==4.66.1
167 |       - typer==0.9.0
168 |       - typing-inspect==0.9.0
169 |       - tzdata==2023.3
170 |       - tzlocal==4.3.1
171 |       - urllib3==1.26.16
172 |       - uvicorn==0.23.2
173 |       - uvloop==0.17.0
174 |       - validators==0.22.0
175 |       - watchdog==3.0.0
176 |       - watchfiles==0.20.0
177 |       - websockets==11.0.3
178 |       - yarl==1.9.2
179 | prefix: /home/fcremer29/miniconda3/envs/ds_llm_bq
180 | 


--------------------------------------------------------------------------------
/docs/ds_llm_bq_92223.yml:
--------------------------------------------------------------------------------
  1 | name: ds_llm_bq
  2 | channels:
  3 |   - conda-forge
  4 |   - defaults
  5 | dependencies:
  6 |   - _libgcc_mutex=0.1=main
  7 |   - _openmp_mutex=5.1=1_gnu
  8 |   - asttokens=2.4.0=pyhd8ed1ab_0
  9 |   - backcall=0.2.0=pyh9f0ad1d_0
 10 |   - backports=1.0=pyhd8ed1ab_3
 11 |   - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
 12 |   - bzip2=1.0.8=h7b6447c_0
 13 |   - ca-certificates=2023.7.22=hbcca054_0
 14 |   - comm=0.1.4=pyhd8ed1ab_0
 15 |   - debugpy=1.6.7=py311h6a678d5_0
 16 |   - decorator=5.1.1=pyhd8ed1ab_0
 17 |   - exceptiongroup=1.1.3=pyhd8ed1ab_0
 18 |   - executing=1.2.0=pyhd8ed1ab_0
 19 |   - importlib-metadata=6.8.0=pyha770c72_0
 20 |   - importlib_metadata=6.8.0=hd8ed1ab_0
 21 |   - ipykernel=6.25.2=pyh2140261_0
 22 |   - ipython=8.15.0=pyh0d859eb_0
 23 |   - jedi=0.19.0=pyhd8ed1ab_0
 24 |   - jupyter_client=8.3.1=pyhd8ed1ab_0
 25 |   - jupyter_core=5.3.1=py311h38be061_0
 26 |   - ld_impl_linux-64=2.38=h1181459_1
 27 |   - libffi=3.4.4=h6a678d5_0
 28 |   - libgcc-ng=11.2.0=h1234567_1
 29 |   - libgomp=11.2.0=h1234567_1
 30 |   - libsodium=1.0.18=h36c2ea0_1
 31 |   - libstdcxx-ng=11.2.0=h1234567_1
 32 |   - libuuid=1.41.5=h5eee18b_0
 33 |   - matplotlib-inline=0.1.6=pyhd8ed1ab_0
 34 |   - ncurses=6.4=h6a678d5_0
 35 |   - nest-asyncio=1.5.6=pyhd8ed1ab_0
 36 |   - openssl=3.0.10=h7f8727e_2
 37 |   - packaging=23.1=pyhd8ed1ab_0
 38 |   - parso=0.8.3=pyhd8ed1ab_0
 39 |   - pexpect=4.8.0=pyh1a96a4e_2
 40 |   - pickleshare=0.7.5=py_1003
 41 |   - pip=23.2.1=py311h06a4308_0
 42 |   - platformdirs=3.10.0=pyhd8ed1ab_0
 43 |   - prompt-toolkit=3.0.39=pyha770c72_0
 44 |   - prompt_toolkit=3.0.39=hd8ed1ab_0
 45 |   - psutil=5.9.0=py311h5eee18b_0
 46 |   - ptyprocess=0.7.0=pyhd3deb0d_0
 47 |   - pure_eval=0.2.2=pyhd8ed1ab_0
 48 |   - pygments=2.16.1=pyhd8ed1ab_0
 49 |   - python=3.11.5=h955ad1f_0
 50 |   - python-dateutil=2.8.2=pyhd8ed1ab_0
 51 |   - python_abi=3.11=2_cp311
 52 |   - pyzmq=25.1.0=py311h6a678d5_0
 53 |   - readline=8.2=h5eee18b_0
 54 |   - setuptools=68.0.0=py311h06a4308_0
 55 |   - six=1.16.0=pyh6c4a22f_0
 56 |   - sqlite=3.41.2=h5eee18b_0
 57 |   - stack_data=0.6.2=pyhd8ed1ab_0
 58 |   - tk=8.6.12=h1ccaba5_0
 59 |   - tornado=6.3.2=py311h5eee18b_0
 60 |   - traitlets=5.10.0=pyhd8ed1ab_0
 61 |   - typing-extensions=4.8.0=hd8ed1ab_0
 62 |   - typing_extensions=4.8.0=pyha770c72_0
 63 |   - wcwidth=0.2.6=pyhd8ed1ab_0
 64 |   - wheel=0.38.4=py311h06a4308_0
 65 |   - xz=5.4.2=h5eee18b_0
 66 |   - zeromq=4.3.4=h9c3ff4c_1
 67 |   - zipp=3.16.2=pyhd8ed1ab_0
 68 |   - zlib=1.2.13=h5eee18b_0
 69 |   - pip:
 70 |       - aiohttp==3.8.5
 71 |       - aiosignal==1.3.1
 72 |       - altair==5.1.1
 73 |       - anyio==4.0.0
 74 |       - async-timeout==4.0.3
 75 |       - attrs==23.1.0
 76 |       - backoff==2.2.1
 77 |       - bcrypt==4.0.1
 78 |       - blinker==1.6.2
 79 |       - cachetools==5.3.1
 80 |       - certifi==2023.7.22
 81 |       - charset-normalizer==3.2.0
 82 |       - chroma-hnswlib==0.7.3
 83 |       - chromadb==0.4.11
 84 |       - click==8.1.7
 85 |       - coloredlogs==15.0.1
 86 |       - dataclasses-json==0.5.14
 87 |       - db-dtypes==1.1.1
 88 |       - fastapi==0.99.1
 89 |       - filelock==3.12.4
 90 |       - flatbuffers==23.5.26
 91 |       - frozenlist==1.4.0
 92 |       - fsspec==2023.9.1
 93 |       - gitdb==4.0.10
 94 |       - gitpython==3.1.36
 95 |       - google-api-core==2.11.1
 96 |       - google-auth==2.23.0
 97 |       - google-cloud-bigquery==3.11.4
 98 |       - google-cloud-bigquery-storage==2.22.0
 99 |       - google-cloud-core==2.3.3
100 |       - google-crc32c==1.5.0
101 |       - google-resumable-media==2.6.0
102 |       - googleapis-common-protos==1.60.0
103 |       - greenlet==2.0.2
104 |       - grpcio==1.58.0
105 |       - grpcio-status==1.58.0
106 |       - h11==0.14.0
107 |       - httptools==0.6.0
108 |       - huggingface-hub==0.16.4
109 |       - humanfriendly==10.0
110 |       - idna==3.4
111 |       - importlib-resources==6.0.1
112 |       - jinja2==3.1.2
113 |       - jsonschema==4.19.1
114 |       - jsonschema-specifications==2023.7.1
115 |       - langchain==0.0.295
116 |       - langsmith==0.0.38
117 |       - markdown-it-py==3.0.0
118 |       - markupsafe==2.1.3
119 |       - marshmallow==3.20.1
120 |       - mdurl==0.1.2
121 |       - monotonic==1.6
122 |       - mpmath==1.3.0
123 |       - multidict==6.0.4
124 |       - mypy-extensions==1.0.0
125 |       - numexpr==2.8.6
126 |       - numpy==1.26.0
127 |       - onnxruntime==1.15.1
128 |       - openai==0.28.0
129 |       - overrides==7.4.0
130 |       - pandas==2.1.0
131 |       - pillow==9.5.0
132 |       - posthog==3.0.2
133 |       - proto-plus==1.22.3
134 |       - protobuf==4.24.3
135 |       - pulsar-client==3.3.0
136 |       - pyarrow==13.0.0
137 |       - pyasn1==0.5.0
138 |       - pyasn1-modules==0.3.0
139 |       - pydantic==1.10.12
140 |       - pydeck==0.8.0
141 |       - pympler==1.0.1
142 |       - pypika==0.48.9
143 |       - python-dotenv==1.0.0
144 |       - pytz==2023.3.post1
145 |       - pytz-deprecation-shim==0.1.0.post0
146 |       - pyyaml==6.0.1
147 |       - referencing==0.30.2
148 |       - regex==2023.8.8
149 |       - requests==2.31.0
150 |       - rich==13.5.3
151 |       - rpds-py==0.10.3
152 |       - rsa==4.9
153 |       - smmap==5.0.1
154 |       - sniffio==1.3.0
155 |       - sqlalchemy==1.4.49
156 |       - sqlalchemy-bigquery==1.8.0
157 |       - starlette==0.27.0
158 |       - streamlit==1.26.0
159 |       - sympy==1.12
160 |       - tabulate==0.9.0
161 |       - tenacity==8.2.3
162 |       - tiktoken==0.5.1
163 |       - tokenizers==0.14.0
164 |       - toml==0.10.2
165 |       - toolz==0.12.0
166 |       - tqdm==4.66.1
167 |       - typer==0.9.0
168 |       - typing-inspect==0.9.0
169 |       - tzdata==2023.3
170 |       - tzlocal==4.3.1
171 |       - urllib3==1.26.16
172 |       - uvicorn==0.23.2
173 |       - uvloop==0.17.0
174 |       - validators==0.22.0
175 |       - watchdog==3.0.0
176 |       - watchfiles==0.20.0
177 |       - websockets==11.0.3
178 |       - yarl==1.9.2
179 | prefix: /home/fcremer29/miniconda3/envs/ds_llm_bq
180 | 


--------------------------------------------------------------------------------
/docs/ds_llm_sql_91923.yml:
--------------------------------------------------------------------------------
  1 | name: ds_llm_sql
  2 | channels:
  3 |   - conda-forge
  4 |   - defaults
  5 | dependencies:
  6 |   - _libgcc_mutex=0.1=main
  7 |   - _openmp_mutex=5.1=1_gnu
  8 |   - asttokens=2.4.0=pyhd8ed1ab_0
  9 |   - backcall=0.2.0=pyh9f0ad1d_0
 10 |   - backports=1.0=pyhd8ed1ab_3
 11 |   - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
 12 |   - bzip2=1.0.8=h7b6447c_0
 13 |   - ca-certificates=2023.7.22=hbcca054_0
 14 |   - comm=0.1.4=pyhd8ed1ab_0
 15 |   - debugpy=1.6.7=py311h6a678d5_0
 16 |   - decorator=5.1.1=pyhd8ed1ab_0
 17 |   - exceptiongroup=1.1.3=pyhd8ed1ab_0
 18 |   - executing=1.2.0=pyhd8ed1ab_0
 19 |   - importlib-metadata=6.8.0=pyha770c72_0
 20 |   - importlib_metadata=6.8.0=hd8ed1ab_0
 21 |   - ipykernel=6.25.2=pyh2140261_0
 22 |   - ipython=8.15.0=pyh0d859eb_0
 23 |   - jedi=0.19.0=pyhd8ed1ab_0
 24 |   - jupyter_client=8.3.1=pyhd8ed1ab_0
 25 |   - jupyter_core=5.3.1=py311h38be061_0
 26 |   - ld_impl_linux-64=2.38=h1181459_1
 27 |   - libffi=3.4.4=h6a678d5_0
 28 |   - libgcc-ng=11.2.0=h1234567_1
 29 |   - libgomp=11.2.0=h1234567_1
 30 |   - libsodium=1.0.18=h36c2ea0_1
 31 |   - libstdcxx-ng=11.2.0=h1234567_1
 32 |   - libuuid=1.41.5=h5eee18b_0
 33 |   - matplotlib-inline=0.1.6=pyhd8ed1ab_0
 34 |   - ncurses=6.4=h6a678d5_0
 35 |   - nest-asyncio=1.5.6=pyhd8ed1ab_0
 36 |   - openssl=3.0.10=h7f8727e_2
 37 |   - packaging=23.1=pyhd8ed1ab_0
 38 |   - parso=0.8.3=pyhd8ed1ab_0
 39 |   - pexpect=4.8.0=pyh1a96a4e_2
 40 |   - pickleshare=0.7.5=py_1003
 41 |   - pip=23.2.1=py311h06a4308_0
 42 |   - platformdirs=3.10.0=pyhd8ed1ab_0
 43 |   - prompt-toolkit=3.0.39=pyha770c72_0
 44 |   - prompt_toolkit=3.0.39=hd8ed1ab_0
 45 |   - psutil=5.9.0=py311h5eee18b_0
 46 |   - ptyprocess=0.7.0=pyhd3deb0d_0
 47 |   - pure_eval=0.2.2=pyhd8ed1ab_0
 48 |   - pygments=2.16.1=pyhd8ed1ab_0
 49 |   - python=3.11.5=h955ad1f_0
 50 |   - python-dateutil=2.8.2=pyhd8ed1ab_0
 51 |   - python_abi=3.11=2_cp311
 52 |   - pyzmq=25.1.0=py311h6a678d5_0
 53 |   - readline=8.2=h5eee18b_0
 54 |   - setuptools=68.0.0=py311h06a4308_0
 55 |   - six=1.16.0=pyh6c4a22f_0
 56 |   - sqlite=3.41.2=h5eee18b_0
 57 |   - stack_data=0.6.2=pyhd8ed1ab_0
 58 |   - tk=8.6.12=h1ccaba5_0
 59 |   - tornado=6.3.2=py311h5eee18b_0
 60 |   - traitlets=5.10.0=pyhd8ed1ab_0
 61 |   - typing-extensions=4.8.0=hd8ed1ab_0
 62 |   - typing_extensions=4.8.0=pyha770c72_0
 63 |   - tzdata=2023c=h04d1e81_0
 64 |   - wcwidth=0.2.6=pyhd8ed1ab_0
 65 |   - wheel=0.38.4=py311h06a4308_0
 66 |   - xz=5.4.2=h5eee18b_0
 67 |   - zeromq=4.3.4=h9c3ff4c_1
 68 |   - zipp=3.16.2=pyhd8ed1ab_0
 69 |   - zlib=1.2.13=h5eee18b_0
 70 |   - pip:
 71 |       - aiohttp==3.8.5
 72 |       - aiosignal==1.3.1
 73 |       - annotated-types==0.5.0
 74 |       - async-timeout==4.0.3
 75 |       - attrs==23.1.0
 76 |       - certifi==2023.7.22
 77 |       - charset-normalizer==3.2.0
 78 |       - dataclasses-json==0.5.14
 79 |       - frozenlist==1.4.0
 80 |       - greenlet==2.0.2
 81 |       - idna==3.4
 82 |       - langchain==0.0.293
 83 |       - langsmith==0.0.38
 84 |       - marshmallow==3.20.1
 85 |       - multidict==6.0.4
 86 |       - mypy-extensions==1.0.0
 87 |       - numexpr==2.8.6
 88 |       - numpy==1.26.0
 89 |       - openai==0.28.0
 90 |       - pydantic==2.3.0
 91 |       - pydantic-core==2.6.3
 92 |       - pymysql==1.1.0
 93 |       - pyyaml==6.0.1
 94 |       - requests==2.31.0
 95 |       - sqlalchemy==2.0.20
 96 |       - tenacity==8.2.3
 97 |       - tqdm==4.66.1
 98 |       - typing-inspect==0.9.0
 99 |       - urllib3==2.0.4
100 |       - yarl==1.9.2
101 | prefix: /home/fcremer29/miniconda3/envs/ds_llm_sql
102 | 


--------------------------------------------------------------------------------
/docs/ds_llm_sql_92023.yml:
--------------------------------------------------------------------------------
  1 | name: ds_llm_sql
  2 | channels:
  3 |   - conda-forge
  4 |   - defaults
  5 | dependencies:
  6 |   - _libgcc_mutex=0.1=main
  7 |   - _openmp_mutex=5.1=1_gnu
  8 |   - asttokens=2.4.0=pyhd8ed1ab_0
  9 |   - backcall=0.2.0=pyh9f0ad1d_0
 10 |   - backports=1.0=pyhd8ed1ab_3
 11 |   - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
 12 |   - bzip2=1.0.8=h7b6447c_0
 13 |   - ca-certificates=2023.7.22=hbcca054_0
 14 |   - comm=0.1.4=pyhd8ed1ab_0
 15 |   - debugpy=1.6.7=py311h6a678d5_0
 16 |   - decorator=5.1.1=pyhd8ed1ab_0
 17 |   - exceptiongroup=1.1.3=pyhd8ed1ab_0
 18 |   - executing=1.2.0=pyhd8ed1ab_0
 19 |   - importlib-metadata=6.8.0=pyha770c72_0
 20 |   - importlib_metadata=6.8.0=hd8ed1ab_0
 21 |   - ipykernel=6.25.2=pyh2140261_0
 22 |   - ipython=8.15.0=pyh0d859eb_0
 23 |   - jedi=0.19.0=pyhd8ed1ab_0
 24 |   - jupyter_client=8.3.1=pyhd8ed1ab_0
 25 |   - jupyter_core=5.3.1=py311h38be061_0
 26 |   - ld_impl_linux-64=2.38=h1181459_1
 27 |   - libffi=3.4.4=h6a678d5_0
 28 |   - libgcc-ng=11.2.0=h1234567_1
 29 |   - libgomp=11.2.0=h1234567_1
 30 |   - libsodium=1.0.18=h36c2ea0_1
 31 |   - libstdcxx-ng=11.2.0=h1234567_1
 32 |   - libuuid=1.41.5=h5eee18b_0
 33 |   - matplotlib-inline=0.1.6=pyhd8ed1ab_0
 34 |   - ncurses=6.4=h6a678d5_0
 35 |   - nest-asyncio=1.5.6=pyhd8ed1ab_0
 36 |   - openssl=3.0.10=h7f8727e_2
 37 |   - packaging=23.1=pyhd8ed1ab_0
 38 |   - parso=0.8.3=pyhd8ed1ab_0
 39 |   - pexpect=4.8.0=pyh1a96a4e_2
 40 |   - pickleshare=0.7.5=py_1003
 41 |   - pip=23.2.1=py311h06a4308_0
 42 |   - platformdirs=3.10.0=pyhd8ed1ab_0
 43 |   - prompt-toolkit=3.0.39=pyha770c72_0
 44 |   - prompt_toolkit=3.0.39=hd8ed1ab_0
 45 |   - psutil=5.9.0=py311h5eee18b_0
 46 |   - ptyprocess=0.7.0=pyhd3deb0d_0
 47 |   - pure_eval=0.2.2=pyhd8ed1ab_0
 48 |   - pygments=2.16.1=pyhd8ed1ab_0
 49 |   - python=3.11.5=h955ad1f_0
 50 |   - python-dateutil=2.8.2=pyhd8ed1ab_0
 51 |   - python_abi=3.11=2_cp311
 52 |   - pyzmq=25.1.0=py311h6a678d5_0
 53 |   - readline=8.2=h5eee18b_0
 54 |   - setuptools=68.0.0=py311h06a4308_0
 55 |   - six=1.16.0=pyh6c4a22f_0
 56 |   - sqlite=3.41.2=h5eee18b_0
 57 |   - stack_data=0.6.2=pyhd8ed1ab_0
 58 |   - tk=8.6.12=h1ccaba5_0
 59 |   - tornado=6.3.2=py311h5eee18b_0
 60 |   - traitlets=5.10.0=pyhd8ed1ab_0
 61 |   - typing-extensions=4.8.0=hd8ed1ab_0
 62 |   - typing_extensions=4.8.0=pyha770c72_0
 63 |   - wcwidth=0.2.6=pyhd8ed1ab_0
 64 |   - wheel=0.38.4=py311h06a4308_0
 65 |   - xz=5.4.2=h5eee18b_0
 66 |   - zeromq=4.3.4=h9c3ff4c_1
 67 |   - zipp=3.16.2=pyhd8ed1ab_0
 68 |   - zlib=1.2.13=h5eee18b_0
 69 |   - pip:
 70 |       - aiohttp==3.8.5
 71 |       - aiosignal==1.3.1
 72 |       - altair==5.1.1
 73 |       - annotated-types==0.5.0
 74 |       - async-timeout==4.0.3
 75 |       - attrs==23.1.0
 76 |       - blinker==1.6.2
 77 |       - cachetools==5.3.1
 78 |       - certifi==2023.7.22
 79 |       - charset-normalizer==3.2.0
 80 |       - click==8.1.7
 81 |       - dataclasses-json==0.5.14
 82 |       - frozenlist==1.4.0
 83 |       - gitdb==4.0.10
 84 |       - gitpython==3.1.36
 85 |       - greenlet==2.0.2
 86 |       - idna==3.4
 87 |       - jinja2==3.1.2
 88 |       - jsonschema==4.19.1
 89 |       - jsonschema-specifications==2023.7.1
 90 |       - langchain==0.0.293
 91 |       - langsmith==0.0.38
 92 |       - markdown-it-py==3.0.0
 93 |       - markupsafe==2.1.3
 94 |       - marshmallow==3.20.1
 95 |       - mdurl==0.1.2
 96 |       - multidict==6.0.4
 97 |       - mypy-extensions==1.0.0
 98 |       - numexpr==2.8.6
 99 |       - numpy==1.26.0
100 |       - openai==0.28.0
101 |       - pandas==2.1.0
102 |       - pillow==9.5.0
103 |       - protobuf==4.24.3
104 |       - pyarrow==13.0.0
105 |       - pydantic==2.3.0
106 |       - pydantic-core==2.6.3
107 |       - pydeck==0.8.0
108 |       - pympler==1.0.1
109 |       - pymysql==1.1.0
110 |       - pytz==2023.3.post1
111 |       - pytz-deprecation-shim==0.1.0.post0
112 |       - pyyaml==6.0.1
113 |       - referencing==0.30.2
114 |       - requests==2.31.0
115 |       - rich==13.5.3
116 |       - rpds-py==0.10.3
117 |       - smmap==5.0.1
118 |       - sqlalchemy==2.0.20
119 |       - streamlit==1.26.0
120 |       - tenacity==8.2.3
121 |       - toml==0.10.2
122 |       - toolz==0.12.0
123 |       - tqdm==4.66.1
124 |       - typing-inspect==0.9.0
125 |       - tzdata==2023.3
126 |       - tzlocal==4.3.1
127 |       - urllib3==2.0.4
128 |       - validators==0.22.0
129 |       - watchdog==3.0.0
130 |       - yarl==1.9.2
131 | prefix: /home/fcremer29/miniconda3/envs/ds_llm_sql
132 | 


--------------------------------------------------------------------------------
/packages/paths.py:
--------------------------------------------------------------------------------
 1 | import os
 2 | from pathlib import Path
 3 | 
 4 | class DS_LLM_PATHS():
 5 |     def __init__(self) -> None:
 6 | 
 7 |         # Root directory of the project
 8 |         self.BASE_DIR = Path(__file__).resolve().parent.parent
 9 |         
10 |         # Credentials folder
11 |         self.CREDENTIALS = os.path.join(self.BASE_DIR, 'credentials') 
12 | 
13 |         # Path to OPENAI
14 |         self.OPEN_AI = os.path.join(self.CREDENTIALS, 'openai_keys.json')
15 | 
16 |         # Path to DB credentials and values
17 |         self.EXTRACT_KEYS = os.path.join(self.CREDENTIALS, 'db_keys.json')
18 | 
19 |         # Path to DB credentials and values
20 |         self.GCP_KEYS = os.path.join(self.CREDENTIALS, 'gcp_keys.json')
21 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
 1 | langchain==0.0.295
 2 | pyarrow==13.0.0
 3 | fsspec==2023.9.1
 4 | google-api-core==2.11.1
 5 | sqlalchemy==1.4.49
 6 | sqlalchemy==1.4.49
 7 | sqlalchemy-bigquery==1.8.0
 8 | google-auth==2.23.0
 9 | google-cloud-bigquery==3.11.4
10 | google-cloud-bigquery-storage==2.22.0
11 | google-cloud-core==2.3.3
12 | python-dotenv
13 | streamlit
14 | 


--------------------------------------------------------------------------------
/test_envs.py:
--------------------------------------------------------------------------------
 1 | from dotenv import load_dotenv
 2 | import os
 3 | import json
 4 | import base64
 5 | 
 6 | load_dotenv()
 7 | 
 8 | PROJECT_ID = os.environ.get("PROJECT_ID_GCP")
 9 | DATASET_ID = os.environ.get("DATASET_BQ")
10 | OPENAI_KEY = os.environ.get("OPENAI_API_KEY")
11 | GCP_KEYS_JSON = os.environ.get("GCP_KEYS_JSON")
12 | 
13 | 
14 | service_key = json.dumps(GCP_KEYS_JSON)
15 | 
16 | # encode service key
17 | encoded_service_key = base64.b64encode(service_key.encode('utf-8'))
18 | 
19 | print(encoded_service_key)
20 | 
21 | 


--------------------------------------------------------------------------------