diff --git a/docs/conf.py b/docs/conf.py index dc5cde16..e99f88df 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -11,10 +11,11 @@ sys.path.insert(0, os.path.abspath("..")) -project = "Dataherald" +project = "Dataherald AI" copyright = "2023, Dataherald" author = "Dataherald" -release = "0.0.1" +release = "main" +html_title = project # -- General configuration --------------------------------------------------- # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration diff --git a/docs/envars.rst b/docs/envars.rst new file mode 100644 index 00000000..632c9976 --- /dev/null +++ b/docs/envars.rst @@ -0,0 +1,33 @@ +Environment Variables +======================= + + +# Openai info. All these fields are required for the engine to work. +OPENAI_API_KEY = #This field is required for the engine to work. +ORG_ID = +LLM_MODEL = 'gpt-4-32k' #the openAI llm model that you want to use. possible values: gpt-4-32k, gpt-4, gpt-3.5-turbo, gpt-3.5-turbo-16k + + +GOLDEN_RECORD_COLLECTION = 'my-golden-records' +#Pinecone info. These fields are required if the vector store used is Pinecone +PINECONE_API_KEY = +PINECONE_ENVIRONMENT = + +# Module implementations to be used names for each required component. You can use the default ones or create your own +API_SERVER = "dataherald.api.fastapi.FastAPI" +SQL_GENERATOR = "dataherald.sql_generator.dataherald_sqlagent.DataheraldSQLAgent" +EVALUATOR = "dataherald.eval.simple_evaluator.SimpleEvaluator" +DB = "dataherald.db.mongo.MongoDB" +VECTOR_STORE = 'dataherald.vector_store.chroma.Chroma' +CONTEXT_STORE = 'dataherald.context_store.default.DefaultContextStore' # Set a context store class, the default one is DefaultContextStore +DB_SCANNER = 'dataherald.db_scanner.sqlalchemy.SqlAlchemyScanner' + +# mongo database information +MONGODB_URI = "mongodb://admin:admin@mongodb:27017" +MONGODB_DB_NAME = 'dataherald' +MONGODB_DB_USERNAME = 'admin' +MONGODB_DB_PASSWORD = 'admin' + + +# The enncryption key is used to encrypt database connection info before storing in Mongo. Please refer to the README on how to set it. +ENCRYPT_KEY = \ No newline at end of file diff --git a/docs/getting_started.rst b/docs/getting_started.rst deleted file mode 100644 index 4c0fe45c..00000000 --- a/docs/getting_started.rst +++ /dev/null @@ -1,19 +0,0 @@ -.. _getting_started: - -Getting started -======================== - -Dataherald AI comes "batteries included." While the engine is modular and core modules can be easily replaced, we have included best-in-class implementations of core modules so you can get set up in minutes. - - - -.. toctree:: - :hidden: - - introduction - quickstart - - - - - diff --git a/docs/index.rst b/docs/index.rst index 1b5ceb23..d3c360c4 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -7,14 +7,38 @@ Dataherald AI ======================================== Welcome to the official documentation page of the Dataherald AI engine. This documentation is intended for developers who want to: -* Use the Dataherald AI engine to set up Natural Language interfaces from structured data in their own projects. -* Contribute to the Dataherald AI engine. +* 🖥️ Use the Dataherald AI engine to set up Natural Language interfaces from structured data in their own projects. +* 🏍️ Contribute to the Dataherald AI engine. These documents will cover how to get started, how to set up an API from your database that can answer questions in plain English and how to extend the core engine's functionality. +We also have an active Discord community you can join + +.. toctree:: + :maxdepth: 1 + :caption: Getting Started + :hidden: + + introduction + quickstart + + .. toctree:: + :caption: References :hidden: - getting_started api - modules \ No newline at end of file + envars + modules + +.. toctree:: + :caption: Tutorials + :hidden: + + tutorial.sample_database + tutorial.finetune_sql_generator + tutorial.chatgpt_plugin + + + + \ No newline at end of file diff --git a/docs/introduction.rst b/docs/introduction.rst index 46cfccfc..04f952f0 100644 --- a/docs/introduction.rst +++ b/docs/introduction.rst @@ -12,8 +12,8 @@ You can use Dataherald to: Dataherald is built to: -* Be modular, allowing different implementations of core modules to be plugged-in -* Come batteries included: Have best-in-class implementations for modules like text to SQL, evaluation -* Be easy to set-up and use with major data warehouses -* Allow for Active Learning, allowing you to improve the performance with usage -* Be fast +* 🔌 Be modular, allowing different implementations of core modules to be plugged-in +* 🔋 Come batteries included: Have best-in-class implementations for modules like text to SQL, evaluation +* 📀 Be easy to set-up and use with major data warehouses +* 👨‍🏫 Allow for Active Learning, allowing you to improve the performance with usage +* 🏎️ Be fast diff --git a/docs/tutorial.chatgpt_plugin.rst b/docs/tutorial.chatgpt_plugin.rst new file mode 100644 index 00000000..ebbea8f0 --- /dev/null +++ b/docs/tutorial.chatgpt_plugin.rst @@ -0,0 +1,4 @@ +Create a ChatGPT plug-in from your structured data +===================================================== + +Coming soon ... \ No newline at end of file diff --git a/docs/tutorial.finetune_sql_generator.rst b/docs/tutorial.finetune_sql_generator.rst new file mode 100644 index 00000000..47f2af0c --- /dev/null +++ b/docs/tutorial.finetune_sql_generator.rst @@ -0,0 +1,4 @@ +Using a Custom Text to SQL Engine +================================== + +Coming soon ... \ No newline at end of file diff --git a/docs/tutorial.sample_database.rst b/docs/tutorial.sample_database.rst new file mode 100644 index 00000000..65a8fd8a --- /dev/null +++ b/docs/tutorial.sample_database.rst @@ -0,0 +1,4 @@ +Setting up a sample Database for accurate NL-to-SQL +==================================================== + +Coming soon ... \ No newline at end of file