Push embedchain-fastdash

.gitignore

@@ -0,0 +1,160 @@
+# 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/

Dockerfile

@@ -0,0 +1,5 @@
+FROM python:3.10
+ADD . /app
+WORKDIR /app
+RUN pip3 install -r requirements.txt --no-cache-dir
+CMD exec gunicorn app:server --bind :7860

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Kedar Dabhadkar
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -8,4 +8,28 @@ pinned: false
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Embedchain 🤝 Fast Dash
+
+[![Open in colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/dkedar7/fast_dash/blob/docs/docs/Examples/03_chat_over_documents.ipynb)  <a href="https://deploy.cloud.run"><img src="https://deploy.cloud.run/button.svg" alt="Run on Google Cloud" width="125"></a>
+
+Extract information from custom sources—web pages, YouTube videos, PDF files, and any chunk of custom text.
+
+Input your sources and let GPT3.5 find answers. This app uses [Embedchain](embedchain.ai), which abstracts the entire process of loading and chunking datasets, creating embeddings, and storing them in a vector database. Embedchain itself uses Langchain and OpenAI's ChatGPT API.
+
+Don't forget to check out [Embedchain](embedchain.ai) team's amazing work!
+
+Fast Dash makes is easy to build any LLM-powered web app with just a few lines of code Here's how an Embedchain app built with Fast Dash looks:
+
+![EmbedchainxFastDash](https://storage.googleapis.com/fast_dash/0.2.2/embedchainfastdash.png)
+Demo hosted [here](https://chatdocs.dkedar.com/)
+
+## Try it yourself
+
+- Run the app in Google Colab: [![Open in colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/dkedar7/fast_dash/blob/docs/docs/Examples/03_chat_over_documents.ipynb)
+- Deploy to your Google Cloud instance by clicking <a href="https://deploy.cloud.run"><img src="https://deploy.cloud.run/button.svg" alt="Run on Google Cloud" width="125"></a>
+
+## About Fast Dash
+
+Fast Dash is a Python module that makes the development of web applications fast and easy. It can build web interfaces for Machine Learning models or to showcase any proof of concept without the hassle of developing UI from scratch.
+
+Check out Fast Dash at https://github.com/dkedar7/fast_dash.

app.py

@@ -0,0 +1,102 @@
+import os
+from fast_dash import FastDash, Fastify, dcc, dmc
+
+from embedchain import App
+from embedchain.config import QueryConfig
+from string import Template
+
+# Define app configurations
+PROMPT = Template(
+    """Use the given context to answer the question at the end.
+If you don't know the answer, say so, but don't try to make one up.
+At the end of the answer, also give the sources as a bulleted list.
+Display the answer as markdown text.
+
+Context: $context
+
+Query: $query
+
+Answer:"""
+)
+query_config = QueryConfig(template=PROMPT, number_documents=5, max_tokens=2000, model="gpt-4")
+
+# Define components
+openai_api_key_component = Fastify(
+    dmc.PasswordInput(
+        placeholder="API Key",
+        description="Get yours at https://platform.openai.com/account/api-keys",
+        required=True
+    ),
+    "value",
+)
+
+web_page_urls_component = Fastify(
+    dmc.MultiSelect(
+        description="Include all the reference web URLs",
+        placeholder="Enter URLs separated by commas",
+        searchable=True,
+        creatable=True,
+    ),
+    "data",
+)
+
+text_component = Fastify(
+    dmc.Textarea(placeholder="Write your query here", autosize=True, minRows=4, description="Any additional information that could be useful"), "value"
+)
+
+query_component = Fastify(
+    dmc.Textarea(placeholder="Write your query here", autosize=True, minRows=4, required=True, description="Write your query here"), "value",
+)
+
+answer_component = Fastify(dcc.Markdown(style={"text-align": "left", "padding": "1%"}, link_target="_blank"), "children")
+
+
+def explore_your_knowledge_base(
+    openai_api_key: openai_api_key_component,
+    web_page_urls: web_page_urls_component,
+    youtube_urls: web_page_urls_component,
+    pdf_urls: web_page_urls_component,
+    text: text_component,
+    query: text_component,
+) -> answer_component:
+    """
+    Input your sources and let GPT3.5 find answers. Built with Fast Dash.
+    This app uses embedchain.ai, which abstracts the entire process of loading and chunking datasets, creating embeddings, and storing them in a vector database.
+    Embedchain itself uses Langchain and OpenAI's ChatGPT API.
+    """
+    os.environ["OPENAI_API_KEY"] = openai_api_key
+
+    try:
+        app = App()
+
+        if not openai_api_key:
+            return "Did you forget adding your OpenAI API key? If you don't have one, you can get it [here](https://platform.openai.com/account/api-keys)."
+
+        if not query:
+            return "Did you forget writing your query in the query box?"
+
+        if web_page_urls:
+            [app.add("web_page", url["value"]) for url in web_page_urls]
+
+        if youtube_urls:
+            [app.add("youtube_video", url["value"]) for url in youtube_urls]
+
+        if pdf_urls:
+            [app.add("pdf_file", url["value"]) for url in pdf_urls]
+
+        if text:
+            app.add_local("text", text)
+
+        answer = app.query(query, query_config)
+
+    except Exception as e:
+        answer = "Oops, something went wrong! Please try again later or make a suggestion [here](https://github.com/dkedar7/embedchain-fastdash/issues)."
+
+    return answer
+
+# Build app (this is all it takes!). Fast Dash understands what it needs to do. 
+app = FastDash(explore_your_knowledge_base, github_url="https://github.com/dkedar7/embedchain-fastdash")
+server = app.server
+
+if __name__ == "__main__":
+    app.run()

requirements.txt

@@ -0,0 +1,3 @@
+fast-dash
+embedchain==0.0.30
+gunicorn