The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
docs: setup docs for embedchain (#287)
Deshraj Yadavc5950034810c
diff --git a/.gitignore b/.gitignoreindex f5f4ae9e9..47eec2706 100644--- a/.gitignore+++ b/.gitignore@@ -170,3 +170,4 @@ db/poetry.lock.idea/+.DS_Storediff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex b99eab454..f4328632a 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -10,8 +10,8 @@ To make a contribution, follow the following steps:2. Do the changes on your fork with dedicated feature branch `feature/f1`3. If you modified the code (new feature or bug-fix), please add tests for it4. Include proper documentation / docstring and examples to run the feature-5. Check the linting-6. Ensure that all tests pass+5. Check the linting+6. Ensure that all tests pass7. Submit a pull requestFor more details about pull requests, please read [GitHub's guides](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request).@@ -25,7 +25,7 @@ Please DO NOT use pip or conda to install the dependencies. Instead, use poetry:```bashpoetry install --all-extras-or+orpoetry install --with dev#activatediff --git a/README.md b/README.mdindex 051a035ab..94cf1adc3 100644--- a/README.md+++ b/README.md@@ -4,647 +4,56 @@[](https://discord.gg/6PzXDgEjG5)[](https://twitter.com/embedchain)[](https://embedchain.substack.com/)+[](https://colab.research.google.com/drive/138lMWhENGeEu7Q1-6lNbNTHGLZXBBz_B?usp=sharing)-embedchain is a framework to easily create LLM powered bots over any dataset. If you want a javascript version, check out [embedchain-js](https://github.com/embedchain/embedchainjs)+Embedchain is a framework to easily create LLM powered bots over any dataset. If you want a javascript version, check out [embedchain-js](https://github.com/embedchain/embedchainjs)-# Table of Contents--- [Latest Updates](#latest-updates)-- [What is embedchain?](#what-is-embedchain)-- [Getting Started](#getting-started)- - [Installation](#installation)- - [Usage](#usage)- - [App Types](#app-types)- - [1. App (uses OpenAI models, paid)](#1-app-uses-openai-models-paid)- - [2. OpenSourceApp (uses opensource models, free)](#2-opensourceapp-uses-opensource-models-free)- - [3. PersonApp (uses OpenAI models, paid)](#3-personapp-uses-openai-models-paid)- - [Add Dataset](#add-dataset)- - [Metadata](#metadata)- - [Interface Types](#interface-types)- - [Query Interface](#query-interface)- - [Chat Interface](#chat-interface)- - [Format supported](#format-supported)- - [Youtube Video](#youtube-video)- - [PDF File](#pdf-file)- - [Web Page](#web-page)- - [Doc File](#doc-file)- - [Text](#text)- - [QnA Pair](#qna-pair)- - [Sitemap](#sitemap)- - [Code Docs Page](#code-docs-page)- - [Reusing a Vector DB](#reusing-a-vector-db)- - [More Formats coming soon](#more-formats-coming-soon)- - [Testing](#testing)-- [Advanced](#advanced)- - [Configuration](#configuration)- - [Example](#example)- - [Configs](#configs)- - [InitConfig](#initconfig)- - [Add Config](#add-config)- - [Query Config](#query-config)- - [Chat Config](#chat-config)- - [Other methods](#other-methods)- - [Reset](#reset)- - [Count](#count)-- [How does it work?](#how-does-it-work)-- [Contribution Guidelines](#contribution-guidelines)-- [Tech Stack](#tech-stack)-- [Team](#team)- - [Author](#author)- - [Maintainer](#maintainer)- - [Citation](#citation)--# Latest Updates--- Introduce a new interface called `chat`. It remembers the history (last 5 messages) and can be used to powerful stateful bots. You can use it by calling `.chat` on any app instance. Works for both OpenAI and OpenSourceApp.--- Introduce a new app type called `OpenSourceApp`. It uses `gpt4all` as the LLM and `sentence transformers` all-MiniLM-L6-v2 as the embedding model. If you use this app, you dont have to pay for anything.--# What is embedchain?--Embedchain abstracts the entire process of loading a dataset, chunking it, creating embeddings and then storing in a vector database.--You can add a single or multiple dataset using `.add` and `.add_local` function and then use `.query` function to find an answer from the added datasets.--If you want to create a Naval Ravikant bot which has 1 youtube video, 1 book as pdf and 2 of his blog posts, as well as a question and answer pair you supply, all you need to do is add the links to the videos, pdf and blog posts and the QnA pair and embedchain will create a bot for you.--```python--from embedchain import App--naval_chat_bot = App()--# Embed Online Resources-naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44")-naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")-naval_chat_bot.add("web_page", "https://nav.al/feedback")-naval_chat_bot.add("web_page", "https://nav.al/agi")--# Embed Local Resources-naval_chat_bot.add_local("qna_pair", ("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."))--naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?")-# answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.-```--# Getting Started--## Installation--First make sure that you have the package installed. If not, then install it using `pip`+## π§ Quick install```bashpip install embedchain```-## Usage--Creating a chatbot involves 3 steps:--- Import the App instance (App Types)-- Add Dataset (Add Dataset)-- Query or Chat on the dataset and get answers (Interface Types)--### App Types--We have three types of App.--#### 1. App (uses OpenAI models, paid)--```python-from embedchain import App--naval_chat_bot = App()-```--- `App` uses OpenAI's model, so these are paid models. You will be charged for embedding model usage and LLM usage.--- `App` uses OpenAI's embedding model to create embeddings for chunks and ChatGPT API as LLM to get answer given the relevant docs. Make sure that you have an OpenAI account and an API key. If you have don't have an API key, you can create one by visiting [this link](https://platform.openai.com/account/api-keys).--- Once you have the API key, set it in an environment variable called `OPENAI_API_KEY`--```python-import os-os.environ["OPENAI_API_KEY"] = "sk-xxxx"-```--#### 2. OpenSourceApp (uses opensource models, free)--```python-from embedchain import OpenSourceApp--naval_chat_bot = OpenSourceApp()-```--- `OpenSourceApp` uses open source embedding and LLM model. It uses `all-MiniLM-L6-v2` from Sentence Transformers library as the embedding model and `gpt4all` as the LLM.--- Here there is no need to setup any api keys. You just need to install embedchain package and these will get automatically installed.--- Once you have imported and instantiated the app, every functionality from here onwards is the same for either type of app.--#### 3. PersonApp (uses OpenAI models, paid)--```python-from embedchain import PersonApp--naval_chat_bot = PersonApp("name_of_person_or_character") #Like "Yoda"-```--- `PersonApp` uses OpenAI's model, so these are paid models. You will be charged for embedding model usage and LLM usage.--- `PersonApp` uses OpenAI's embedding model to create embeddings for chunks and ChatGPT API as LLM to get answer given the relevant docs. Make sure that you have an OpenAI account and an API key. If you have don't have an API key, you can create one by visiting [this link](https://platform.openai.com/account/api-keys).--- Once you have the API key, set it in an environment variable called `OPENAI_API_KEY`--```python-import os-os.environ["OPENAI_API_KEY"] = "sk-xxxx"-```--### Add Dataset--- This step assumes that you have already created an `app` instance by either using `App` or `OpenSourceApp`. We are calling our app instance as `naval_chat_bot`--- Now use `.add` function to add any dataset.--```python--# naval_chat_bot = App() or-# naval_chat_bot = OpenSourceApp()--# Embed Online Resources-naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44")-naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")-naval_chat_bot.add("web_page", "https://nav.al/feedback")-naval_chat_bot.add("web_page", "https://nav.al/agi")--# Embed Local Resources-naval_chat_bot.add_local("qna_pair", ("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."))-```--- If there is any other app instance in your script or app, you can change the import as--```python-from embedchain import App as EmbedChainApp-from embedchain import OpenSourceApp as EmbedChainOSApp-from embedchain import PersonApp as EmbedChainPersonApp--# or--from embedchain import App as ECApp-from embedchain import OpenSourceApp as ECOSApp-from embedchain import PersonApp as ECPApp-```-### Metadata--- You can also add metadata to your datasets by passing a `metadata` parameter in the `.add` or `.add_local` function.--```python-metadata = {- 'author': 'John Doe',- 'category': 'Sample Data',- 'date': '2023-07-15',- 'source': 'Data Repository',- 'description': 'This is an example dataset for testing purposes.'-}--naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44", metadata=metadata)-```--- The `metadata` parameter expects a dictionary object where the keys represent metadata attributes, and the values represent corresponding metadata values-## Interface Types--### Query Interface--- This interface is like a question answering bot. It takes a question and gets the answer. It does not maintain context about the previous chats.--- To use this, call `.query` function to get the answer for any query.--```python-print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?"))-# answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.-```--### Chat Interface--- This interface is chat interface where it remembers previous conversation. Right now it remembers 5 conversation by default.--- To use this, call `.chat` function to get the answer for any query.--```python-print(naval_chat_bot.chat("How to be happy in life?"))-# answer: The most important trick to being happy is to realize happiness is a skill you develop and a choice you make. You choose to be happy, and then you work at it. It's just like building muscles or succeeding at your job. It's about recognizing the abundance and gifts around you at all times.--print(naval_chat_bot.chat("who is naval ravikant?"))-# answer: Naval Ravikant is an Indian-American entrepreneur and investor.--print(naval_chat_bot.chat("what did the author say about happiness?"))-# answer: The author, Naval Ravikant, believes that happiness is a choice you make and a skill you develop. He compares the mind to the body, stating that just as the body can be molded and changed, so can the mind. He emphasizes the importance of being present in the moment and not getting caught up in regrets of the past or worries about the future. By being present and grateful for where you are, you can experience true happiness.-```--### Stream Response--- You can add config to your query method to stream responses like ChatGPT does. You would require a downstream handler to render the chunk in your desirable format. Supports both OpenAI model and OpenSourceApp.--- To use this, instantiate a `QueryConfig` or `ChatConfig` object with `stream=True`. Then pass it to the `.chat()` or `.query()` method. The following example iterates through the chunks and prints them as they appear.--```python-app = App()-query_config = QueryConfig(stream = True)-resp = app.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?", query_config)--for chunk in resp:- print(chunk, end="", flush=True)-# answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.-```--## Format supported--We support the following formats:--### Youtube Video--To add any youtube video to your app, use the data_type (first argument to `.add`) as `youtube_video`. Eg:--```python-app.add('youtube_video', 'a_valid_youtube_url_here')-```--### PDF File--To add any pdf file, use the data_type as `pdf_file`. Eg:--```python-app.add('pdf_file', 'a_valid_url_where_pdf_file_can_be_accessed')-```--Note that we do not support password protected pdfs.--### Web Page--To add any web page, use the data_type as `web_page`. Eg:--```python-app.add('web_page', 'a_valid_web_page_url')-```--### Doc File--To add any doc/docx file, use the data_type as `docx`. Eg:--```python-app.add('docx', 'a_local_docx_file_path')-```--### Text+## π Demo-To supply your own text, use the data_type as `text` and enter a string. The text is not processed, this can be very versatile. Eg:+Try out PandasAI in your browser:-```python-app.add_local('text', 'Seek wealth, not money or status. Wealth is having assets that earn while you sleep. Money is how we transfer time and wealth. Status is your place in the social hierarchy.')-```--Note: This is not used in the examples because in most cases you will supply a whole paragraph or file, which did not fit.--### QnA Pair--To supply your own QnA pair, use the data_type as `qna_pair` and enter a tuple. Eg:--```python-app.add_local('qna_pair', ("Question", "Answer"))-```-### Sitemap--To add a XML site map containing list of all urls, use the data_type as `sitemap` and enter the sitemap url. Eg:--```python-app.add('sitemap', 'a_valid_sitemap_url/sitemap.xml')-```--### Code Docs Page--To add a code documentation page, use the data_type as `code_docs_page` and enter the url. Eg:--```python-app.add("code_docs_page", "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/cassandra")-```--### Reusing a Vector DB--Default behavior is to create a persistent vector DB in the directory **./db**. You can split your application into two Python scripts: one to create a local vector DB and the other to reuse this local persistent vector DB. This is useful when you want to index hundreds of documents and separately implement a chat interface.--Create a local index:--```python--from embedchain import App--naval_chat_bot = App()-naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44")-naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")-```--You can reuse the local index with the same code, but without adding new documents:--```python--from embedchain import App+[](https://colab.research.google.com/drive/138lMWhENGeEu7Q1-6lNbNTHGLZXBBz_B?usp=sharing)-naval_chat_bot = App()-print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?"))-```--### More Formats coming soon--- If you want to add any other format, please create an [issue](https://github.com/embedchain/embedchain/issues) and we will add it to the list of supported formats.--## Testing--Before you consume valueable tokens, you should make sure that the embedding you have done works and that it's receiving the correct document from the database.--For this you can use the `dry_run` method.--Following the example above, add this to your script:--```python-print(naval_chat_bot.dry_run('Can you tell me who Naval Ravikant is?'))--'''-Use the following pieces of context to answer the query at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.- Q: Who is Naval Ravikant?-A: Naval Ravikant is an Indian-American entrepreneur and investor.- Query: Can you tell me who Naval Ravikant is?- Helpful Answer:-'''-```--_The embedding is confirmed to work as expected. It returns the right document, even if the question is asked slightly different. No prompt tokens have been consumed._--**The dry run will still consume tokens to embed your query, but it is only ~1/15 of the prompt.**--## Colab Notebook and Video Tutorials--Chinese Colab Tutorial:https://colab.research.google.com/drive/10_7Y0x4YXWVjuhhYwVraGQLpKAatTQTm?usp=sharing--Chinese Video Tutorial:https://www.bilibili.com/video/BV1YX4y1H7oN+## π Documentation-# Advanced+The documentation for PandasAI can be found at [docs.embedchain.ai](https://docs.embedchain.ai).-## Configuration+## π» Usage-Embedchain is made to work out of the box. However, for advanced users we're also offering configuration options. All of these configuration options are optional and have sane defaults.+Embedchain empowers you to create chatbot models similar to ChatGPT, using your own evolving dataset.-### Example+### Queries-Here's the readme example with configuration options.+For example, you can use Embedchain to create an Elon Musk bot using the following code:```pythonimport osfrom embedchain import App-from embedchain.config import InitConfig, AddConfig, QueryConfig-from chromadb.utils import embedding_functions--# Example: use your own embedding function-config = InitConfig(ef=embedding_functions.OpenAIEmbeddingFunction(- api_key=os.getenv("OPENAI_API_KEY"),- organization_id=os.getenv("OPENAI_ORGANIZATION"),- model_name="text-embedding-ada-002"- ))-naval_chat_bot = App(config)--# Example: define your own chunker config for `youtube_video`-youtube_add_config = {- "chunker": {- "chunk_size": 1000,- "chunk_overlap": 100,- "length_function": len,- }-}-naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44", AddConfig(**youtube_add_config))--add_config = AddConfig()-naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf", add_config)-naval_chat_bot.add("web_page", "https://nav.al/feedback", add_config)-naval_chat_bot.add("web_page", "https://nav.al/agi", add_config)--naval_chat_bot.add_local("qna_pair", ("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."), add_config)--query_config = QueryConfig() # Currently no options-print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?", query_config))-```--Here's the example of using custom prompt template with `.query`--```python-from embedchain.config import QueryConfig-from embedchain.embedchain import App-from string import Template-import wikipedia--einstein_chat_bot = App()--# Embed Wikipedia page-page = wikipedia.page("Albert Einstein")-einstein_chat_bot.add("text", page.content)--# Example: use your own custom template with `$context` and `$query`-einstein_chat_template = Template("""- You are Albert Einstein, a German-born theoretical physicist,- widely ranked among the greatest and most influential scientists of all time.-- Use the following information about Albert Einstein to respond to- the human's query acting as Albert Einstein.- Context: $context-- Keep the response brief. If you don't know the answer, just say that you don't know, don't try to make up an answer.-- Human: $query- Albert Einstein:""")-query_config = QueryConfig(einstein_chat_template)-queries = [- "Where did you complete your studies?",- "Why did you win nobel prize?",- "Why did you divorce your first wife?",-]-for query in queries:- response = einstein_chat_bot.query(query, query_config)- print("Query: ", query)- print("Response: ", response)--# Output-# Query: Where did you complete your studies?-# Response: I completed my secondary education at the Argovian cantonal school in Aarau, Switzerland.-# Query: Why did you win nobel prize?-# Response: I won the Nobel Prize in Physics in 1921 for my services to Theoretical Physics, particularly for my discovery of the law of the photoelectric effect.-# Query: Why did you divorce your first wife?-# Response: We divorced due to living apart for five years.-```--**Client Mode**. By defining a (ChromaDB) server, you can run EmbedChain as a client only.--```python-from embedchain import App-config = InitConfig(host="localhost", port="8080")-app = App(config)-```-This is useful for scalability. Say you have EmbedChain behind an API with multiple workers. If you separate clients and server, all clients can connect to the server, which only has to keep one instance of the database in memory. You also don't have to worry about replication.--To run a chroma db server, run `git clone https://github.com/chroma-core/chroma.git`, navigate to the directory (`cd chroma`) and then start the server with `docker-compose up -d --build`.--### Configs--This section describes all possible config options.--#### **InitConfig**--|option|description|type|default|-|---|---|---|---|-|log_level|log level|string|WARNING|-|ef|embedding function|chromadb.utils.embedding_functions|{text-embedding-ada-002}|-|db|vector database (experimental)|BaseVectorDB|ChromaDB|-|host|hostname for (Chroma) DB server|string|None|-|port|port number for (Chroma) DB server|string, int|None|--#### **Add Config**--|option|description|type|default|-|---|---|---|---|-|chunker|chunker config|ChunkerConfig|Default values for chunker depends on the `data_type`. Please refer [ChunkerConfig](#chunker-config)|-|loader|loader config|LoaderConfig|None|--##### **Chunker Config**--|option|description|type|default|-|---|---|---|---|-|chunk_size|Maximum size of chunks to return|int|Default value for various `data_type` mentioned below|-|chunk_overlap|Overlap in characters between chunks|int|Default value for various `data_type` mentioned below|-|length_function|Function that measures the length of given chunks|typing.Callable|Default value for various `data_type` mentioned below|--Default values of chunker config parameters for different `data_type`:--|data_type|chunk_size|chunk_overlap|length_function|-|---|---|---|---|-|docx|1000|0|len|-|text|300|0|len|-|qna_pair|300|0|len|-|web_page|500|0|len|-|pdf_file|1000|0|len|-|youtube_video|2000|0|len|--##### **Loader Config**--_coming soon_--#### **Query Config**--|option|description|type|default|-|---|---|---|---|-|number_documents|number of documents to be retrieved as context|int|1|-|template|custom template for prompt|Template|Template("Use the following pieces of context to answer the query at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. \$context Query: $query Helpful Answer:")|-|history|include conversation history from your client or database|any (recommendation: list[str])|None-|stream|control if response is streamed back to the user|bool|False|-|model|OpenAI model|string|gpt-3.5-turbo-0613|-|temperature|creativity of the model (0-1)|float|0|-|max_tokens|limit maximum tokens used|int|1000|-|top_p|diversity of words used by the model (0-1)|float|1|--#### **Chat Config**--All options for query and...--_coming soon_--history is handled automatically, the config option is not supported.--## Other methods--### Reset--Resets the database and deletes all embeddings. Irreversible. Requires reinitialization afterwards.--```python-app.reset()-```-### Count+# Create a bot instance+os.environ["OPENAI_API_KEY"] = "YOUR API KEY"+elon_bot = App()-Counts the number of embeddings (chunks) in the database.+# Embed online resources+elon_bot.add("web_page", "https://en.wikipedia.org/wiki/Elon_Musk")+elon_bot.add("web_page", "https://tesla.com/elon-musk")+elon_bot.add("youtube_video", "https://www.youtube.com/watch?v=MxZpaJK74Y4")-```python-print(app.count())-# returns: 481+# Query the bot+elon_bot.query("How many companies does Elon Musk run?")+# Answer: Elon Musk runs four companies: Tesla, SpaceX, Neuralink, and The Boring Company```-# How does it work?--Creating a chat bot over any dataset needs the following steps to happen--- load the data-- create meaningful chunks-- create embeddings for each chunk-- store the chunks in vector database--Whenever a user asks any query, following process happens to find the answer for the query--- create the embedding for query-- find similar documents for this query from vector database-- pass similar documents as context to LLM to get the final answer.--The process of loading the dataset and then querying involves multiple steps and each steps has nuances of it is own.--- How should I chunk the data? What is a meaningful chunk size?-- How should I create embeddings for each chunk? Which embedding model should I use?-- How should I store the chunks in vector database? Which vector database should I use?-- Should I store meta data along with the embeddings?-- How should I find similar documents for a query? Which ranking model should I use?--These questions may be trivial for some but for a lot of us, it needs research, experimentation and time to find out the accurate answers.--embedchain is a framework which takes care of all these nuances and provides a simple interface to create bots over any dataset.--In the first release, we are making it easier for anyone to get a chatbot over any dataset up and running in less than a minute. All you need to do is create an app instance, add the data sets using `.add` function and then use `.query` function to get the relevant answer.--# Contribution Guidelines--Thank you for your interest in contributing to the EmbedChain project! We welcome your ideas and contributions to help improve the project. Please follow the instructions below to get started:--1. **Fork the repository**: Click on the "Fork" button at the top right corner of this repository page. This will create a copy of the repository in your own GitHub account.--2. **Install the required dependencies**: Ensure that you have the necessary dependencies installed in your Python environment. You can do this by running the following command:--```bash-make install-```--3. **Make changes in the code**: Create a new branch in your forked repository and make your desired changes in the codebase.-4. **Format code**: Before creating a pull request, it's important to ensure that your code follows our formatting guidelines. Run the following commands to format the code:--```bash-make lint format-```--5. **Create a pull request**: When you are ready to contribute your changes, submit a pull request to the EmbedChain repository. Provide a clear and descriptive title for your pull request, along with a detailed description of the changes you have made.--# Tech Stack--embedchain is built on the following stack:--- [Langchain](https://github.com/hwchase17/langchain) as an LLM framework to load, chunk and index data-- [OpenAI's Ada embedding model](https://platform.openai.com/docs/guides/embeddings) to create embeddings-- [OpenAI's ChatGPT API](https://platform.openai.com/docs/guides/gpt/chat-completions-api) as LLM to get answers given the context-- [Chroma](https://github.com/chroma-core/chroma) as the vector database to store embeddings-- [gpt4all](https://github.com/nomic-ai/gpt4all) as an open source LLM-- [sentence-transformers](https://huggingface.co/sentence-transformers) as open source embedding model--# Team--## Author--- Taranjeet Singh ([@taranjeetio](https://twitter.com/taranjeetio))--## Maintainer+## π€ Contributing-- [cachho](https://github.com/cachho)+Contributions are welcome! Please check out the issues on the repository, and feel free to open a pull request.+For more information, please see the [contributing guidelines](CONTRIBUTING.md).## Citationdiff --git a/docs/README.md b/docs/README.mdnew file mode 100644index 000000000..e322686dc--- /dev/null+++ b/docs/README.md@@ -0,0 +1,25 @@+# Contributing to embedchain docs+++### π©βπ» Development++Install the [Mintlify CLI](https://www.npmjs.com/package/mintlify) to preview the documentation changes locally. To install, use the following command++```+npm i -g mintlify+```++Run the following command at the root of your documentation (where mint.json is)++```+mintlify dev+```++### π Publishing Changes++Changes will be deployed to production automatically after your PR is merged to the main branch.++#### Troubleshooting++- Mintlify dev isn't running - Run `mintlify install` it'll re-install dependencies.+- Page loads as a 404 - Make sure you are running in a folder with `mint.json`diff --git a/docs/advanced/advanced_usage.mdx b/docs/advanced/advanced_usage.mdxnew file mode 100644index 000000000..a8677103e--- /dev/null+++ b/docs/advanced/advanced_usage.mdx@@ -0,0 +1,138 @@+---+title: 'π± App types'+---++Creating a chatbot involves 3 steps:++- βοΈ Import the App instance+- ποΈ Add Dataset+- π¬ Query or Chat on the dataset and get answers (Interface Types)++## App Types++We have three types of App.++### App++```python+from embedchain import App+naval_chat_bot = App()+```++- `App` uses OpenAI's model, so these are paid models. πΈ You will be charged for embedding model usage and LLM usage.++- `App` uses OpenAI's embedding model to create embeddings for chunks and ChatGPT API as LLM to get answer given the relevant docs. Make sure that you have an OpenAI account and an API key. If you have don't have an API key, you can create one by visiting [this link](https://platform.openai.com/account/api-keys).++- Once you have the API key, set it in an environment variable called `OPENAI_API_KEY`++```python+import os+os.environ["OPENAI_API_KEY"] = "sk-xxxx"+```++### OpenSourceApp++```python+from embedchain import OpenSourceApp+naval_chat_bot = OpenSourceApp()+```++- `OpenSourceApp` uses open source embedding and LLM model. It uses `all-MiniLM-L6-v2` from Sentence Transformers library as the embedding model and `gpt4all` as the LLM.+- Here there is no need to setup any api keys. You just need to install embedchain package and these will get automatically installed. π¦+- Once you have imported and instantiated the app, every functionality from here onwards is the same for either type of app. π++### PersonApp++```python+from embedchain import PersonApp+naval_chat_bot = PersonApp("name_of_person_or_character") #Like "Yoda"+```++- `PersonApp` uses OpenAI's model, so these are paid models. πΈ You will be charged for embedding model usage and LLM usage.+- `PersonApp` uses OpenAI's embedding model to create embeddings for chunks and ChatGPT API as LLM to get answer given the relevant docs. Make sure that you have an OpenAI account and an API key. If you have don't have an API key, you can create one by visiting [this link](https://platform.openai.com/account/api-keys).+- Once you have the API key, set it in an environment variable called `OPENAI_API_KEY`++```python+import os+os.environ["OPENAI_API_KEY"] = "sk-xxxx"+```++## Add Dataset++- This step assumes that you have already created an `app` instance by either using `App` or `OpenSourceApp`. We are calling our app instance as `naval_chat_bot` π€++- Now use `.add()` function to add any dataset.++```python+# naval_chat_bot = App() or+# naval_chat_bot = OpenSourceApp()++# Embed Online Resources+naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44")+naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")+naval_chat_bot.add("web_page", "https://nav.al/feedback")+naval_chat_bot.add("web_page", "https://nav.al/agi")++# Embed Local Resources+naval_chat_bot.add_local("qna_pair", ("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."))+```++- If there is any other app instance in your script or app, you can change the import as++```python+from embedchain import App as EmbedChainApp+from embedchain import OpenSourceApp as EmbedChainOSApp+from embedchain import PersonApp as EmbedChainPersonApp++# or++from embedchain import App as ECApp+from embedchain import OpenSourceApp as ECOSApp+from embedchain import PersonApp as ECPApp+```++## Interface Types++### Query Interface++- This interface is like a question answering bot. It takes a question and gets the answer. It does not maintain context about the previous chats.β++- To use this, call `.query()` function to get the answer for any query.++```python+print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?"))+# answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.+```++### Chat Interface++- This interface is chat interface where it remembers previous conversation. Right now it remembers 5 conversation by default. π¬++- To use this, call `.chat` function to get the answer for any query.++```python+print(naval_chat_bot.chat("How to be happy in life?"))+# answer: The most important trick to being happy is to realize happiness is a skill you develop and a choice you make. You choose to be happy, and then you work at it. It's just like building muscles or succeeding at your job. It's about recognizing the abundance and gifts around you at all times.++print(naval_chat_bot.chat("who is naval ravikant?"))+# answer: Naval Ravikant is an Indian-American entrepreneur and investor.++print(naval_chat_bot.chat("what did the author say about happiness?"))+# answer: The author, Naval Ravikant, believes that happiness is a choice you make and a skill you develop. He compares the mind to the body, stating that just as the body can be molded and changed, so can the mind. He emphasizes the importance of being present in the moment and not getting caught up in regrets of the past or worries about the future. By being present and grateful for where you are, you can experience true happiness.+```++### Stream Response++- You can add config to your query method to stream responses like ChatGPT does. You would require a downstream handler to render the chunk in your desirable format. Supports both OpenAI model and OpenSourceApp. π++- To use this, instantiate a `QueryConfig` or `ChatConfig` object with `stream=True`. Then pass it to the `.chat()` or `.query()` method. The following example iterates through the chunks and prints them as they appear.++```python+app = App()+query_config = QueryConfig(stream = True)+resp = app.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?", query_config)++for chunk in resp:+ print(chunk, end="", flush=True)+# answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.+```diff --git a/docs/advanced/configuration.mdx b/docs/advanced/configuration.mdxnew file mode 100644index 000000000..5c912b099--- /dev/null+++ b/docs/advanced/configuration.mdx@@ -0,0 +1,114 @@+---+title: 'βοΈ Custom configurations'+---++Embedchain is made to work out of the box. However, for advanced users we're also offering configuration options. All of these configuration options are optional and have sane defaults.++## Examples++### Custom embedding function++Here's the readme example with configuration options.++```python+import os+from embedchain import App+from embedchain.config import InitConfig, AddConfig, QueryConfig+from chromadb.utils import embedding_functions++# Example: use your own embedding function+config = InitConfig(ef=embedding_functions.OpenAIEmbeddingFunction(+ api_key=os.getenv("OPENAI_API_KEY"),+ organization_id=os.getenv("OPENAI_ORGANIZATION"),+ model_name="text-embedding-ada-002"+ ))+naval_chat_bot = App(config)++# Example: define your own chunker config for `youtube_video`+youtube_add_config = {+ "chunker": {+ "chunk_size": 1000,+ "chunk_overlap": 100,+ "length_function": len,+ }+}+naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44", AddConfig(**youtube_add_config))++add_config = AddConfig()+naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf", add_config)+naval_chat_bot.add("web_page", "https://nav.al/feedback", add_config)+naval_chat_bot.add("web_page", "https://nav.al/agi", add_config)++naval_chat_bot.add_local("qna_pair", ("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."), add_config)++query_config = QueryConfig() # Currently no options+print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?", query_config))+```++### Custom prompt template++Here's the example of using custom prompt template with `.query`++```python+from embedchain.config import QueryConfig+from embedchain.embedchain import App+from string import Template+import wikipedia++einstein_chat_bot = App()++# Embed Wikipedia page+page = wikipedia.page("Albert Einstein")+einstein_chat_bot.add("text", page.content)++# Example: use your own custom template with `$context` and `$query`+einstein_chat_template = Template("""+ You are Albert Einstein, a German-born theoretical physicist,+ widely ranked among the greatest and most influential scientists of all time.++ Use the following information about Albert Einstein to respond to+ the human's query acting as Albert Einstein.+ Context: $context++ Keep the response brief. If you don't know the answer, just say that you don't know, don't try to make up an answer.++ Human: $query+ Albert Einstein:""")+query_config = QueryConfig(einstein_chat_template)+queries = [+ "Where did you complete your studies?",+ "Why did you win nobel prize?",+ "Why did you divorce your first wife?",+]+for query in queries:+ response = einstein_chat_bot.query(query, query_config)+ print("Query: ", query)+ print("Response: ", response)++# Output+# Query: Where did you complete your studies?+# Response: I completed my secondary education at the Argovian cantonal school in Aarau, Switzerland.+# Query: Why did you win nobel prize?+# Response: I won the Nobel Prize in Physics in 1921 for my services to Theoretical Physics, particularly for my discovery of the law of the photoelectric effect.+# Query: Why did you divorce your first wife?+# Response: We divorced due to living apart for five years.+```++## Other methods++### Reset++Resets the database and deletes all embeddings. Irreversible. Requires reinitialization afterwards.++```python+app.reset()+```++### Count++Counts the number of embeddings (chunks) in the database.++```python+print(app.count())+# returns: 481+```diff --git a/docs/advanced/data_types.mdx b/docs/advanced/data_types.mdxnew file mode 100644index 000000000..123a41d8f--- /dev/null+++ b/docs/advanced/data_types.mdx@@ -0,0 +1,84 @@+---+title: 'π Supported data formats'+---++Embedchain supports following data formats:++### Youtube video++To add any youtube video to your app, use the data_type (first argument to `.add()` method) as `youtube_video`. Eg:++```python+app.add('youtube_video', 'a_valid_youtube_url_here')+```++### PDF file++To add any pdf file, use the data_type as `pdf_file`. Eg:++```python+app.add('pdf_file', 'a_valid_url_where_pdf_file_can_be_accessed')+```++Note that we do not support password protected pdfs.++### Web page++To add any web page, use the data_type as `web_page`. Eg:++```python+app.add('web_page', 'a_valid_web_page_url')+```++### Doc file++To add any doc/docx file, use the data_type as `docx`. Eg:++```python+app.add('docx', 'a_local_docx_file_path')+```++### Text++To supply your own text, use the data_type as `text` and enter a string. The text is not processed, this can be very versatile. Eg:++```python+app.add_local('text', 'Seek wealth, not money or status. Wealth is having assets that earn while you sleep. Money is how we transfer time and wealth. Status is your place in the social hierarchy.')+```++Note: This is not used in the examples because in most cases you will supply a whole paragraph or file, which did not fit.++### QnA pair++To supply your own QnA pair, use the data_type as `qna_pair` and enter a tuple. Eg:++```python+app.add_local('qna_pair', ("Question", "Answer"))+```++## Reusing a vector database++Default behavior is to create a persistent vector DB in the directory **./db**. You can split your application into two Python scripts: one to create a local vector DB and the other to reuse this local persistent vector DB. This is useful when you want to index hundreds of documents and separately implement a chat interface.++Create a local index:++```python+from embedchain import App++naval_chat_bot = App()+naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44")+naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")+```++You can reuse the local index with the same code, but without adding new documents:++```python+from embedchain import App++naval_chat_bot = App()+print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?"))+```++### More formats (coming soon!)++- If you want to add any other format, please create an [issue](https://github.com/embedchain/embedchain/issues) and we will add it to the list of supported formats.diff --git a/docs/advanced/query_configuration.mdx b/docs/advanced/query_configuration.mdxnew file mode 100644index 000000000..6a75c147b--- /dev/null+++ b/docs/advanced/query_configuration.mdx@@ -0,0 +1,58 @@+---+title: 'π Query configurations'+---++## InitConfig++| option | description | type | default |+|-----------|-----------------------|---------------------------------|------------------------|+| log_level | log level | string | WARNING |+| ef | embedding function | chromadb.utils.embedding_functions | \{text-embedding-ada-002\} |+| db | vector database (experimental) | BaseVectorDB | ChromaDB |+++## AddConfig++|option|description|type|default|+|---|---|---|---|+|chunker|chunker config|ChunkerConfig|Default values for chunker depends on the `data_type`. Please refer [ChunkerConfig](#chunker-config)|+|loader|loader config|LoaderConfig|None|++### ChunkerConfig++|option|description|type|default|+|---|---|---|---|+|chunk_size|Maximum size of chunks to return|int|Default value for various `data_type` mentioned below|+|chunk_overlap|Overlap in characters between chunks|int|Default value for various `data_type` mentioned below|+|length_function|Function that measures the length of given chunks|typing.Callable|Default value for various `data_type` mentioned below|++Default values of chunker config parameters for different `data_type`:++|data_type|chunk_size|chunk_overlap|length_function|+|---|---|---|---|+|docx|1000|0|len|+|text|300|0|len|+|qna_pair|300|0|len|+|web_page|500|0|len|+|pdf_file|1000|0|len|+|youtube_video|2000|0|len|++### LoaderConfig++_coming soon_++## QueryConfig++|option|description|type|default|+|---|---|---|---|+|template|custom template for prompt|Template|Template("Use the following pieces of context to answer the query at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. \$context Query: \$query Helpful Answer:")|+|history|include conversation history from your client or database|any (recommendation: list[str])|None+|stream|control if response is streamed back to the user|bool|False|++## ChatConfig++All options for query and...++_coming soon_++History is handled automatically, the config option is not supported.diff --git a/docs/advanced/showcase.mdx b/docs/advanced/showcase.mdxnew file mode 100644index 000000000..ee7ef464a--- /dev/null+++ b/docs/advanced/showcase.mdx@@ -0,0 +1,57 @@+---+title: 'πͺ Community showcase'+---++Embedchain community has been super active in creating demos on top of Embedchain. On this page, we showcase all the apps, blogs, videos, and tutorials created by the community. β€οΈ++## Apps++### Open Source++- [Discord Bot for LLM chat](https://github.com/Reidond/discord_bots_playground/tree/c8b0c36541e4b393782ee506804c4b6962426dd6/python/chat-channel-bot) by Reidond+- [EmbedChain-Streamlit-Docker App](https://github.com/amjadraza/embedchain-streamlit-app) by amjadraza+- [Harry Potter Philosphers Stone Bot](https://github.com/vinayak-kempawad/Harry_Potter_Philosphers_Stone_Bot/) by Vinayak Kempawad, ([linkedin post](https://www.linkedin.com/feed/update/urn:li:activity:7080907532155686912/))+- [LLM bot trained on own messages](https://github.com/Harin329/harinBot) by Hao Wu++### Closed Source++- [Taobot.io](https://taobot.io) - chatbot & knowledgebase hybrid by [cachho](https://github.com/cachho)++## Templates++### Replit+- [Embedchain Chat Bot](https://replit.com/@taranjeet1/Embedchain-Chat-Bot) by taranjeetio+- [Embedchain Memory Chat Bot Template](https://replit.com/@taranjeetio/Embedchain-Memory-Chat-Bot-Template) by taranjeetio++## Posts++### Blogs++- [Customer Service LINE Bot](https://www.evanlin.com/langchain-embedchain/)+++- [What is embedchain](https://www.linkedin.com/posts/activity-7079393104423698432-wRyi/) by Rithesh Sreenivasan+- [Building a chatbot with EmbedChain](https://www.linkedin.com/posts/activity-7078434598984060928-Zdso/) by Lior Sinclair+- [Making chatbot without vs with embedchain](https://www.linkedin.com/posts/kalyanksnlp_llms-chatbots-langchain-activity-7077453416221863936-7N1L/) by Kalyan KS+++- [What is embedchain](https://twitter.com/AlphaSignalAI/status/1672668574450847745) by Lior+- [Building a chatbot with Embedchain](https://twitter.com/Saboo_Shubham_/status/1673537044419686401) by Shubham Saboo++## Videos++- [embedChain Create LLM powered bots over any dataset Python Demo Tesla Neurallink Chatbot Example](https://www.youtube.com/watch?v=bJqAn22a6Gc) by Rithesh Sreenivasan+- [Embedchain - NEW π₯ Langchain BABY to build LLM Bots](https://www.youtube.com/watch?v=qj_GNQ06I8o) by 1littlecoder+- [EmbedChain -- NEW!: Build LLM-Powered Bots with Any Dataset](https://www.youtube.com/watch?v=XmaBezzGHu4) by DataInsightEdge+- [Chat With Your PDFs in less than 10 lines of code! EMBEDCHAIN tutorial](https://www.youtube.com/watch?v=1ugkcsAcw44) by Phani Reddy+- [How To Create A Custom Knowledge AI Powered Bot | Install + How To Use](https://www.youtube.com/watch?v=VfCrIiAst-c) by The Ai Solopreneur+- [Build Custom Chatbot in 6 min with this Framework [Beginner Friendly]](https://www.youtube.com/watch?v=-8HxOpaFySM) by Maya Akim+- [embedchain-streamlit-app](https://www.youtube.com/watch?v=3-9GVd-3v74) by Amjad Raza++## Mentions++### Github repos++- [awesome-ChatGPT-repositories](https://github.com/taishi-i/awesome-ChatGPT-repositories)diff --git a/docs/advanced/testing.mdx b/docs/advanced/testing.mdxnew file mode 100644index 000000000..62dce77ea--- /dev/null+++ b/docs/advanced/testing.mdx@@ -0,0 +1,25 @@+---+title: 'π§ͺ Testing'+---++Before you consume valueable tokens, you should make sure that the embedding you have done works and that it's receiving the correct document from the database.++For this you can use the `dry_run` method.++Following the example above, add this to your script:++```python+print(naval_chat_bot.dry_run('Can you tell me who Naval Ravikant is?'))++'''+Use the following pieces of context to answer the query at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.+ Q: Who is Naval Ravikant?+A: Naval Ravikant is an Indian-American entrepreneur and investor.+ Query: Can you tell me who Naval Ravikant is?+ Helpful Answer:+'''+```++_The embedding is confirmed to work as expected. It returns the right document, even if the question is asked slightly different. No prompt tokens have been consumed._++**The dry run will still consume tokens to embed your query, but it is only ~1/15 of the prompt.**diff --git a/docs/contribution/dev.mdx b/docs/contribution/dev.mdxnew file mode 100644index 000000000..e392b7d47--- /dev/null+++ b/docs/contribution/dev.mdx@@ -0,0 +1,60 @@+---+title: 'π¨βπ» Development'+description: 'Contribute to Embedchain framework development'+---++Thank you for your interest in contributing to the EmbedChain project! We welcome your ideas and contributions to help improve the project. Please follow the instructions below to get started:++1. **Fork the repository**: Click on the "Fork" button at the top right corner of this repository page. This will create a copy of the repository in your own GitHub account.++2. **Install the required dependencies**: Ensure that you have the necessary dependencies installed in your Python environment. You can do this by running the following command:++```bash+make install+```++3. **Make changes in the code**: Create a new branch in your forked repository and make your desired changes in the codebase.+4. **Format code**: Before creating a pull request, it's important to ensure that your code follows our formatting guidelines. Run the following commands to format the code:++```bash+make lint format+```++5. **Create a pull request**: When you are ready to contribute your changes, submit a pull request to the EmbedChain repository. Provide a clear and descriptive title for your pull request, along with a detailed description of the changes you have made.++# Tech Stack++embedchain is built on the following stack:++- [Langchain](https://github.com/hwchase17/langchain) as an LLM framework to load, chunk and index data+- [OpenAI's Ada embedding model](https://platform.openai.com/docs/guides/embeddings) to create embeddings+- [OpenAI's ChatGPT API](https://platform.openai.com/docs/guides/gpt/chat-completions-api) as LLM to get answers given the context+- [Chroma](https://github.com/chroma-core/chroma) as the vector database to store embeddings+- [gpt4all](https://github.com/nomic-ai/gpt4all) as an open source LLM+- [sentence-transformers](https://huggingface.co/sentence-transformers) as open source embedding model++## Team++### Author++- Taranjeet Singh ([@taranjeetio](https://twitter.com/taranjeetio))++### Maintainer++- Deshraj Yadav ([@deshrajdry](https://twitter.com/taranjeetio))+- [cachho](https://github.com/cachho)++### Citation++If you utilize this repository, please consider citing it with:++```+@misc{embedchain,+ author = {Taranjeet Singh},+ title = {Embechain: Framework to easily create LLM powered bots over any dataset},+ year = {2023},+ publisher = {GitHub},+ journal = {GitHub repository},+ howpublished = {\url{https://github.com/embedchain/embedchain}},+}+```diff --git a/docs/contribution/docs.mdx b/docs/contribution/docs.mdxnew file mode 100644index 000000000..7aa846ec5--- /dev/null+++ b/docs/contribution/docs.mdx@@ -0,0 +1,61 @@+---+title: 'π Documentation'+description: 'Contribute to Embedchain docs'+---++<Info>+ **Prerequisite** You should have installed Node.js (version 18.10.0 or+ higher).+</Info>++Step 1. Install Mintlify on your OS:++<CodeGroup>++```bash npm+npm i -g mintlify+```++```bash yarn+yarn global add mintlify+```++</CodeGroup>++Step 2. Go to the `docs/` directory (where you can find `mint.json`) and run the following command:++```bash+mintlify dev+```++The documentation website is now available at `http://localhost:3000`.++### Custom Ports++Mintlify uses port 3000 by default. You can use the `--port` flag to customize the port Mintlify runs on. For example, use this command to run in port 3333:++```bash+mintlify dev --port 3333+```++You will see an error like this if you try to run Mintlify in a port that's already taken:++```md+Error: listen EADDRINUSE: address already in use :::3000+```++## Mintlify Versions++Each CLI is linked to a specific version of Mintlify. Please update the CLI if your local website looks different than production.++<CodeGroup>++```bash npm+npm i -g mintlify@latest+```++```bash yarn+yarn global upgrade mintlify+```++</CodeGroup>diff --git a/docs/development.mdx b/docs/development.mdxnew file mode 100644index 000000000..878300893--- /dev/null+++ b/docs/development.mdx@@ -0,0 +1,98 @@+---+title: 'Development'+description: 'Learn how to preview changes locally'+---++<Info>+ **Prerequisite** You should have installed Node.js (version 18.10.0 or+ higher).+</Info>++Step 1. Install Mintlify on your OS:++<CodeGroup>++```bash npm+npm i -g mintlify+```++```bash yarn+yarn global add mintlify+```++</CodeGroup>++Step 2. Go to the docs are located (where you can find `mint.json`) and run the following command:++```bash+mintlify dev+```++The documentation website is now available at `http://localhost:3000`.++### Custom Ports++Mintlify uses port 3000 by default. You can use the `--port` flag to customize the port Mintlify runs on. For example, use this command to run in port 3333:++```bash+mintlify dev --port 3333+```++You will see an error like this if you try to run Mintlify in a port that's already taken:++```md+Error: listen EADDRINUSE: address already in use :::3000+```++## Mintlify Versions++Each CLI is linked to a specific version of Mintlify. Please update the CLI if your local website looks different than production.++<CodeGroup>++```bash npm+npm i -g mintlify@latest+```++```bash yarn+yarn global upgrade mintlify+```++</CodeGroup>++## Deployment++<Tip>+ Unlimited editors available under the [Startup+ Plan](https://mintlify.com/pricing)+</Tip>++You should see the following if the deploy successfully went through:++<Frame>+ <img src="/images/checks-passed.png" style={{ borderRadius: '0.5rem' }} />+</Frame>++## Troubleshooting++Here's how to solve some common problems when working with the CLI.++<AccordionGroup>+ <Accordion title="Mintlify is not loading">+ Update to Node v18. Run `mintlify install` and try again.+ </Accordion>+ <Accordion title="No such file or directory on Windows">+Go to the `C:/Users/Username/.mintlify/` directory and remove the `mint`+folder. Then Open the Git Bash in this location and run `git clone+https://github.com/mintlify/mint.git`.++Repeat step 3.++ </Accordion>+ <Accordion title="Getting an unknown error">+ Try navigating to the root of your device and delete the ~/.mintlify folder.+ Then run `mintlify dev` again.+ </Accordion>+</AccordionGroup>++Curious about what changed in a CLI version? [Check out the CLI changelog.](/changelog/command-line)diff --git a/docs/favicon.png b/docs/favicon.pngnew file mode 100644index 000000000..b03041a08Binary files /dev/null and b/docs/favicon.png differdiff --git a/docs/images/background.png b/docs/images/background.pngnew file mode 100644index 000000000..3292ab271Binary files /dev/null and b/docs/images/background.png differdiff --git a/docs/images/checks-passed.png b/docs/images/checks-passed.pngnew file mode 100644index 000000000..3303c7736Binary files /dev/null and b/docs/images/checks-passed.png differdiff --git a/docs/introduction.mdx b/docs/introduction.mdxnew file mode 100644index 000000000..00f0bb9a3--- /dev/null+++ b/docs/introduction.mdx@@ -0,0 +1,56 @@+---+title: π Introduction+description: 'π Embedchain is a framework to easily create LLM powered bots over any dataset.'+---++## π€ What is Embedchain?++Embedchain abstracts the entire process of loading a dataset, chunking it, creating embeddings, and storing it in a vector database.++You can add a single or multiple datasets using the .add and .add_local functions. Then, simply use the .query function to find answers from the added datasets.++If you want to create a Naval Ravikant bot with a YouTube video, a book in PDF format, two blog posts, and a question and answer pair, all you need to do is add the respective links. Embedchain will take care of the rest, creating a bot for you.++```python+from embedchain import App++naval_chat_bot = App()+# Embed Online Resources+naval_chat_bot.add("youtube_video", "https://www.youtube.com/watch?v=3qHkcs3kG44")+naval_chat_bot.add("pdf_file", "https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")+naval_chat_bot.add("web_page", "https://nav.al/feedback")+naval_chat_bot.add("web_page", "https://nav.al/agi")++# Embed Local Resources+naval_chat_bot.add_local("qna_pair", ("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."))++naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?")+# Answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.+```++## π How it works?++Creating a chat bot over any dataset involves the following steps:++1. Load the data+2. Create meaningful chunks+3. Create embeddings for each chunk+4. Store the chunks in a vector database++When a user asks a query, the following process happens to find the answer:++1. Create an embedding for the query+2. Find similar documents for the query from the vector database+3. Pass the similar documents as context to LLM to get the final answer.++The process of loading the dataset and querying involves multiple steps, each with its own nuances:++- How should I chunk the data? What is a meaningful chunk size?+- How should I create embeddings for each chunk? Which embedding model should I use?+- How should I store the chunks in a vector database? Which vector database should I use?+- Should I store metadata along with the embeddings?+- How should I find similar documents for a query? Which ranking model should I use?++Embedchain takes care of all these nuances and provides a simple interface to create bots over any dataset.++In the first release, we make it easier for anyone to get a chatbot over any dataset up and running in less than a minute. Just create an app instance, add the datasets using the `.add()` function, and use the `.query()` function to get the relevant answers.diff --git a/docs/logo/dark.svg b/docs/logo/dark.svgnew file mode 100644index 000000000..0ee3e9c70--- /dev/null+++ b/docs/logo/dark.svg@@ -0,0 +1,15 @@+<svg width="1612" height="258" viewBox="0 0 1612 258" fill="none" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">+<g clip-path="url(#clip0_2_73)">+<path d="M295 0H0V258H295V0Z" fill="url(#pattern0)"/>+</g>+<path d="M364.912 192V61.0909H450.054V80.9702H388.626V116.51H445.643V136.389H388.626V172.121H450.565V192H364.912ZM473.225 192V93.8182H495.342V110.501H496.492C498.538 104.876 501.925 100.487 506.656 97.3338C511.386 94.1378 517.032 92.5398 523.594 92.5398C530.242 92.5398 535.846 94.1591 540.406 97.3977C545.008 100.594 548.246 104.962 550.121 110.501H551.144C553.317 105.047 556.982 100.7 562.139 97.4616C567.337 94.1804 573.495 92.5398 580.612 92.5398C589.646 92.5398 597.018 95.3949 602.728 101.105C608.438 106.815 611.293 115.146 611.293 126.098V192H588.09V129.678C588.09 123.584 586.471 119.131 583.232 116.318C579.994 113.463 576.031 112.036 571.343 112.036C565.761 112.036 561.393 113.783 558.239 117.277C555.129 120.729 553.573 125.224 553.573 130.764V192H530.881V128.719C530.881 123.648 529.347 119.599 526.279 116.574C523.254 113.548 519.29 112.036 514.39 112.036C511.066 112.036 508.04 112.888 505.313 114.592C502.586 116.254 500.413 118.619 498.793 121.688C497.174 124.713 496.364 128.25 496.364 132.298V192H473.225ZM635.791 192V61.0909H658.93V110.054H659.889C661.082 107.668 662.765 105.132 664.939 102.447C667.112 99.7202 670.052 97.3977 673.76 95.4801C677.467 93.5199 682.197 92.5398 687.95 92.5398C695.535 92.5398 702.375 94.4787 708.468 98.3565C714.605 102.192 719.463 107.881 723.042 115.423C726.664 122.923 728.476 132.128 728.476 143.037C728.476 153.818 726.707 162.98 723.17 170.523C719.633 178.065 714.818 183.818 708.724 187.781C702.63 191.744 695.727 193.726 688.014 193.726C682.389 193.726 677.723 192.788 674.015 190.913C670.308 189.038 667.325 186.78 665.066 184.138C662.85 181.453 661.125 178.918 659.889 176.531H658.547V192H635.791ZM658.483 142.909C658.483 149.259 659.377 154.82 661.167 159.592C663 164.365 665.62 168.094 669.029 170.778C672.481 173.42 676.657 174.741 681.558 174.741C686.672 174.741 690.954 173.378 694.406 170.651C697.858 167.881 700.457 164.109 702.204 159.337C703.994 154.521 704.889 149.045 704.889 142.909C704.889 136.815 704.015 131.403 702.268 126.673C700.521 121.943 697.922 118.236 694.47 115.551C691.018 112.866 686.714 111.524 681.558 111.524C676.615 111.524 672.417 112.824 668.966 115.423C665.514 118.023 662.893 121.666 661.103 126.354C659.356 131.041 658.483 136.56 658.483 142.909ZM791.613 193.918C781.769 193.918 773.268 191.872 766.109 187.781C758.992 183.648 753.516 177.81 749.681 170.267C745.846 162.682 743.928 153.754 743.928 143.484C743.928 133.385 745.846 124.521 749.681 116.893C753.559 109.223 758.971 103.257 765.917 98.9957C772.863 94.6918 781.023 92.5398 790.398 92.5398C796.45 92.5398 802.16 93.5199 807.529 95.4801C812.941 97.3977 817.714 100.381 821.847 104.429C826.023 108.477 829.305 113.634 831.691 119.898C834.077 126.119 835.271 133.534 835.271 142.142V149.237H754.795V133.641H813.09C813.048 129.209 812.089 125.267 810.214 121.815C808.339 118.321 805.718 115.572 802.352 113.57C799.028 111.567 795.15 110.565 790.718 110.565C785.988 110.565 781.833 111.716 778.254 114.017C774.674 116.276 771.883 119.259 769.88 122.966C767.92 126.631 766.918 130.658 766.876 135.047V148.662C766.876 154.372 767.92 159.273 770.008 163.364C772.096 167.412 775.015 170.523 778.765 172.696C782.515 174.827 786.904 175.892 791.933 175.892C795.299 175.892 798.346 175.423 801.073 174.486C803.8 173.506 806.165 172.078 808.168 170.203C810.171 168.328 811.684 166.006 812.707 163.236L834.312 165.665C832.948 171.375 830.349 176.361 826.514 180.622C822.721 184.841 817.863 188.122 811.94 190.466C806.016 192.767 799.241 193.918 791.613 193.918ZM891.281 193.726C883.568 193.726 876.664 191.744 870.571 187.781C864.477 183.818 859.662 178.065 856.125 170.523C852.588 162.98 850.819 153.818 850.819 143.037C850.819 132.128 852.609 122.923 856.189 115.423C859.811 107.881 864.69 102.192 870.826 98.3565C876.963 94.4787 883.802 92.5398 891.345 92.5398C897.098 92.5398 901.828 93.5199 905.535 95.4801C909.243 97.3977 912.183 99.7202 914.356 102.447C916.529 105.132 918.213 107.668 919.406 110.054H920.365V61.0909H943.568V192H920.812V176.531H919.406C918.213 178.918 916.487 181.453 914.228 184.138C911.97 186.78 908.987 189.038 905.279 190.913C901.572 192.788 896.906 193.726 891.281 193.726ZM897.737 174.741C902.637 174.741 906.814 173.42 910.265 170.778C913.717 168.094 916.338 164.365 918.127 159.592C919.917 154.82 920.812 149.259 920.812 142.909C920.812 136.56 919.917 131.041 918.127 126.354C916.38 121.666 913.781 118.023 910.329 115.423C906.92 112.824 902.723 111.524 897.737 111.524C892.581 111.524 888.277 112.866 884.825 115.551C881.373 118.236 878.774 121.943 877.027 126.673C875.279 131.403 874.406 136.815 874.406 142.909C874.406 149.045 875.279 154.521 877.027 159.337C878.816 164.109 881.437 167.881 884.889 170.651C888.383 173.378 892.666 174.741 897.737 174.741ZM1011.05 193.918C1001.25 193.918 992.835 191.766 985.803 187.462C978.815 183.158 973.424 177.213 969.631 169.628C965.881 162 964.006 153.222 964.006 143.293C964.006 133.321 965.924 124.521 969.759 116.893C973.594 109.223 979.006 103.257 985.995 98.9957C993.026 94.6918 1001.34 92.5398 1010.92 92.5398C1018.89 92.5398 1025.95 94.0099 1032.08 96.9503C1038.26 99.848 1043.18 103.96 1046.85 109.287C1050.51 114.571 1052.6 120.75 1053.11 127.824H1031C1030.1 123.094 1027.97 119.152 1024.6 115.999C1021.28 112.803 1016.83 111.205 1011.24 111.205C1006.51 111.205 1002.36 112.483 998.779 115.04C995.2 117.554 992.408 121.176 990.406 125.906C988.445 130.636 987.465 136.304 987.465 142.909C987.465 149.599 988.445 155.352 990.406 160.168C992.366 164.94 995.114 168.626 998.651 171.226C1002.23 173.783 1006.43 175.061 1011.24 175.061C1014.65 175.061 1017.7 174.422 1020.38 173.143C1023.11 171.822 1025.39 169.926 1027.22 167.455C1029.06 164.983 1030.31 161.979 1031 158.442H1053.11C1052.56 165.388 1050.51 171.545 1046.98 176.915C1043.44 182.241 1038.62 186.418 1032.53 189.443C1026.44 192.426 1019.28 193.918 1011.05 193.918ZM1095.25 134.472V192H1072.11V61.0909H1094.74V110.501H1095.89C1098.19 104.962 1101.75 100.594 1106.56 97.3977C1111.42 94.1591 1117.6 92.5398 1125.1 92.5398C1131.92 92.5398 1137.86 93.9673 1142.94 96.8224C1148.01 99.6776 1151.93 103.854 1154.7 109.351C1157.51 114.848 1158.92 121.56 1158.92 129.486V192H1135.78V133.065C1135.78 126.46 1134.07 121.325 1130.66 117.661C1127.3 113.953 1122.57 112.099 1116.47 112.099C1112.38 112.099 1108.72 112.994 1105.48 114.784C1102.28 116.531 1099.77 119.067 1097.94 122.391C1096.15 125.714 1095.25 129.741 1095.25 134.472ZM1210.76 193.982C1204.53 193.982 1198.93 192.874 1193.94 190.658C1189 188.399 1185.08 185.075 1182.18 180.686C1179.33 176.297 1177.9 170.885 1177.9 164.45C1177.9 158.911 1178.92 154.33 1180.97 150.707C1183.01 147.085 1185.81 144.188 1189.34 142.014C1192.88 139.841 1196.86 138.2 1201.3 137.092C1205.77 135.942 1210.39 135.111 1215.17 134.599C1220.92 134.003 1225.58 133.47 1229.16 133.001C1232.74 132.49 1235.34 131.723 1236.96 130.7C1238.62 129.635 1239.46 127.994 1239.46 125.778V125.395C1239.46 120.58 1238.03 116.851 1235.17 114.209C1232.32 111.567 1228.21 110.246 1222.84 110.246C1217.17 110.246 1212.67 111.482 1209.35 113.953C1206.07 116.425 1203.85 119.344 1202.7 122.71L1181.1 119.642C1182.8 113.676 1185.61 108.69 1189.53 104.685C1193.45 100.636 1198.25 97.6108 1203.92 95.608C1209.58 93.5625 1215.85 92.5398 1222.71 92.5398C1227.44 92.5398 1232.15 93.0938 1236.83 94.2017C1241.52 95.3097 1245.81 97.142 1249.68 99.6989C1253.56 102.213 1256.67 105.643 1259.02 109.99C1261.4 114.337 1262.59 119.77 1262.59 126.29V192H1240.35V178.513H1239.58C1238.18 181.24 1236.2 183.797 1233.64 186.183C1231.12 188.527 1227.95 190.423 1224.11 191.872C1220.32 193.278 1215.87 193.982 1210.76 193.982ZM1216.76 176.979C1221.41 176.979 1225.44 176.062 1228.84 174.23C1232.25 172.355 1234.87 169.884 1236.71 166.815C1238.58 163.747 1239.52 160.402 1239.52 156.78V145.21C1238.8 145.807 1237.56 146.361 1235.81 146.872C1234.11 147.384 1232.19 147.831 1230.06 148.214C1227.93 148.598 1225.82 148.939 1223.73 149.237C1221.64 149.536 1219.83 149.791 1218.3 150.004C1214.85 150.473 1211.76 151.24 1209.03 152.305C1206.3 153.371 1204.15 154.862 1202.57 156.78C1201 158.655 1200.21 161.084 1200.21 164.067C1200.21 168.328 1201.76 171.545 1204.87 173.719C1207.99 175.892 1211.95 176.979 1216.76 176.979ZM1285.86 192V93.8182H1309V192H1285.86ZM1297.5 79.8835C1293.83 79.8835 1290.68 78.669 1288.04 76.2401C1285.39 73.7685 1284.07 70.8068 1284.07 67.3551C1284.07 63.8608 1285.39 60.8991 1288.04 58.4702C1290.68 55.9986 1293.83 54.7628 1297.5 54.7628C1301.2 54.7628 1304.36 55.9986 1306.96 58.4702C1309.6 60.8991 1310.92 63.8608 1310.92 67.3551C1310.92 70.8068 1309.6 73.7685 1306.96 76.2401C1304.36 78.669 1301.2 79.8835 1297.5 79.8835ZM1355.93 134.472V192H1332.8V93.8182H1354.91V110.501H1356.06C1358.32 105.004 1361.92 100.636 1366.87 97.3977C1371.85 94.1591 1378.01 92.5398 1385.34 92.5398C1392.11 92.5398 1398.02 93.9886 1403.04 96.8864C1408.12 99.7841 1412.04 103.982 1414.81 109.479C1417.62 114.976 1419 121.645 1418.96 129.486V192H1395.82V133.065C1395.82 126.503 1394.12 121.368 1390.71 117.661C1387.34 113.953 1382.67 112.099 1376.71 112.099C1372.66 112.099 1369.06 112.994 1365.91 114.784C1362.8 116.531 1360.35 119.067 1358.56 122.391C1356.81 125.714 1355.93 129.741 1355.93 134.472Z" fill="white"/>+<defs>+<pattern id="pattern0" patternContentUnits="objectBoundingBox" width="1" height="1">+<use xlink:href="#image0_2_73" transform="scale(0.00746269 0.00833333)"/>+</pattern>+<clipPath id="clip0_2_73">+<rect width="295" height="258" fill="white"/>+</clipPath>+<image id="image0_2_73" width="134" height="120" xlink:href="data:image/png;base64,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"/>+</defs>+</svg>diff --git a/docs/logo/light.svg b/docs/logo/light.svgnew file mode 100644index 000000000..e0881572f--- /dev/null+++ b/docs/logo/light.svg@@ -0,0 +1,15 @@+<svg width="1731" height="258" viewBox="0 0 1731 258" fill="none" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">+<g clip-path="url(#clip0_2_74)">+<path d="M295 0H0V258H295V0Z" fill="url(#pattern0)"/>+</g>+<path d="M354.912 200V69.0909H440.054V88.9702H378.626V124.51H435.643V144.389H378.626V180.121H440.565V200H354.912ZM463.225 200V101.818H485.342V118.501H486.492C488.538 112.876 491.925 108.487 496.656 105.334C501.386 102.138 507.032 100.54 513.594 100.54C520.242 100.54 525.846 102.159 530.406 105.398C535.008 108.594 538.246 112.962 540.121 118.501H541.144C543.317 113.047 546.982 108.7 552.139 105.462C557.337 102.18 563.495 100.54 570.612 100.54C579.646 100.54 587.018 103.395 592.728 109.105C598.438 114.815 601.293 123.146 601.293 134.098V200H578.09V137.678C578.09 131.584 576.471 127.131 573.232 124.318C569.994 121.463 566.031 120.036 561.343 120.036C555.761 120.036 551.393 121.783 548.239 125.277C545.129 128.729 543.573 133.224 543.573 138.764V200H520.881V136.719C520.881 131.648 519.347 127.599 516.279 124.574C513.254 121.548 509.29 120.036 504.39 120.036C501.066 120.036 498.04 120.888 495.313 122.592C492.586 124.254 490.413 126.619 488.793 129.688C487.174 132.713 486.364 136.25 486.364 140.298V200H463.225ZM625.791 200V69.0909H648.93V118.054H649.889C651.082 115.668 652.765 113.132 654.939 110.447C657.112 107.72 660.052 105.398 663.76 103.48C667.467 101.52 672.197 100.54 677.95 100.54C685.535 100.54 692.375 102.479 698.468 106.357C704.605 110.192 709.463 115.881 713.042 123.423C716.664 130.923 718.476 140.128 718.476 151.037C718.476 161.818 716.707 170.98 713.17 178.523C709.633 186.065 704.818 191.818 698.724 195.781C692.63 199.744 685.727 201.726 678.014 201.726C672.389 201.726 667.723 200.788 664.015 198.913C660.308 197.038 657.325 194.78 655.066 192.138C652.85 189.453 651.125 186.918 649.889 184.531H648.547V200H625.791ZM648.483 150.909C648.483 157.259 649.377 162.82 651.167 167.592C653 172.365 655.62 176.094 659.029 178.778C662.481 181.42 666.657 182.741 671.558 182.741C676.672 182.741 680.954 181.378 684.406 178.651C687.858 175.881 690.457 172.109 692.204 167.337C693.994 162.521 694.889 157.045 694.889 150.909C694.889 144.815 694.015 139.403 692.268 134.673C690.521 129.943 687.922 126.236 684.47 123.551C681.018 120.866 676.714 119.524 671.558 119.524C666.615 119.524 662.417 120.824 658.966 123.423C655.514 126.023 652.893 129.666 651.103 134.354C649.356 139.041 648.483 144.56 648.483 150.909ZM781.613 201.918C771.769 201.918 763.268 199.872 756.109 195.781C748.992 191.648 743.516 185.81 739.681 178.267C735.846 170.682 733.928 161.754 733.928 151.484C733.928 141.385 735.846 132.521 739.681 124.893C743.559 117.223 748.971 111.257 755.917 106.996C762.863 102.692 771.023 100.54 780.398 100.54C786.45 100.54 792.16 101.52 797.529 103.48C802.941 105.398 807.714 108.381 811.847 112.429C816.023 116.477 819.305 121.634 821.691 127.898C824.077 134.119 825.271 141.534 825.271 150.142V157.237H744.795V141.641H803.09C803.048 137.209 802.089 133.267 800.214 129.815C798.339 126.321 795.718 123.572 792.352 121.57C789.028 119.567 785.15 118.565 780.718 118.565C775.988 118.565 771.833 119.716 768.254 122.017C764.674 124.276 761.883 127.259 759.88 130.966C757.92 134.631 756.918 138.658 756.876 143.047V156.662C756.876 162.372 757.92 167.273 760.008 171.364C762.096 175.412 765.015 178.523 768.765 180.696C772.515 182.827 776.904 183.892 781.933 183.892C785.299 183.892 788.346 183.423 791.073 182.486C793.8 181.506 796.165 180.078 798.168 178.203C800.171 176.328 801.684 174.006 802.707 171.236L824.312 173.665C822.948 179.375 820.349 184.361 816.514 188.622C812.721 192.841 807.863 196.122 801.94 198.466C796.016 200.767 789.241 201.918 781.613 201.918ZM881.281 201.726C873.568 201.726 866.664 199.744 860.571 195.781C854.477 191.818 849.662 186.065 846.125 178.523C842.588 170.98 840.819 161.818 840.819 151.037C840.819 140.128 842.609 130.923 846.189 123.423C849.811 115.881 854.69 110.192 860.826 106.357C866.963 102.479 873.802 100.54 881.345 100.54C887.098 100.54 891.828 101.52 895.535 103.48C899.243 105.398 902.183 107.72 904.356 110.447C906.529 113.132 908.213 115.668 909.406 118.054H910.365V69.0909H933.568V200H910.812V184.531H909.406C908.213 186.918 906.487 189.453 904.228 192.138C901.97 194.78 898.987 197.038 895.279 198.913C891.572 200.788 886.906 201.726 881.281 201.726ZM887.737 182.741C892.637 182.741 896.814 181.42 900.265 178.778C903.717 176.094 906.338 172.365 908.127 167.592C909.917 162.82 910.812 157.259 910.812 150.909C910.812 144.56 909.917 139.041 908.127 134.354C906.38 129.666 903.781 126.023 900.329 123.423C896.92 120.824 892.723 119.524 887.737 119.524C882.581 119.524 878.277 120.866 874.825 123.551C871.373 126.236 868.774 129.943 867.027 134.673C865.279 139.403 864.406 144.815 864.406 150.909C864.406 157.045 865.279 162.521 867.027 167.337C868.816 172.109 871.437 175.881 874.889 178.651C878.383 181.378 882.666 182.741 887.737 182.741ZM1001.05 201.918C991.251 201.918 982.835 199.766 975.803 195.462C968.815 191.158 963.424 185.213 959.631 177.628C955.881 170 954.006 161.222 954.006 151.293C954.006 141.321 955.924 132.521 959.759 124.893C963.594 117.223 969.006 111.257 975.995 106.996C983.026 102.692 991.336 100.54 1000.92 100.54C1008.89 100.54 1015.95 102.01 1022.08 104.95C1028.26 107.848 1033.18 111.96 1036.85 117.287C1040.51 122.571 1042.6 128.75 1043.11 135.824H1021C1020.1 131.094 1017.97 127.152 1014.6 123.999C1011.28 120.803 1006.83 119.205 1001.24 119.205C996.513 119.205 992.359 120.483 988.779 123.04C985.2 125.554 982.408 129.176 980.406 133.906C978.445 138.636 977.465 144.304 977.465 150.909C977.465 157.599 978.445 163.352 980.406 168.168C982.366 172.94 985.114 176.626 988.651 179.226C992.231 181.783 996.428 183.061 1001.24 183.061C1004.65 183.061 1007.7 182.422 1010.38 181.143C1013.11 179.822 1015.39 177.926 1017.22 175.455C1019.06 172.983 1020.31 169.979 1021 166.442H1043.11C1042.56 173.388 1040.51 179.545 1036.98 184.915C1033.44 190.241 1028.62 194.418 1022.53 197.443C1016.44 200.426 1009.28 201.918 1001.05 201.918ZM1085.25 142.472V200H1062.11V69.0909H1084.74V118.501H1085.89C1088.19 112.962 1091.75 108.594 1096.56 105.398C1101.42 102.159 1107.6 100.54 1115.1 100.54C1121.92 100.54 1127.86 101.967 1132.94 104.822C1138.01 107.678 1141.93 111.854 1144.7 117.351C1147.51 122.848 1148.92 129.56 1148.92 137.486V200H1125.78V141.065C1125.78 134.46 1124.07 129.325 1120.66 125.661C1117.3 121.953 1112.57 120.099 1106.47 120.099C1102.38 120.099 1098.72 120.994 1095.48 122.784C1092.28 124.531 1089.77 127.067 1087.94 130.391C1086.15 133.714 1085.25 137.741 1085.25 142.472ZM1200.76 201.982C1194.53 201.982 1188.93 200.874 1183.94 198.658C1179 196.399 1175.08 193.075 1172.18 188.686C1169.33 184.297 1167.9 178.885 1167.9 172.45C1167.9 166.911 1168.92 162.33 1170.97 158.707C1173.01 155.085 1175.81 152.188 1179.34 150.014C1182.88 147.841 1186.86 146.2 1191.3 145.092C1195.77 143.942 1200.39 143.111 1205.17 142.599C1210.92 142.003 1215.58 141.47 1219.16 141.001C1222.74 140.49 1225.34 139.723 1226.96 138.7C1228.62 137.635 1229.46 135.994 1229.46 133.778V133.395C1229.46 128.58 1228.03 124.851 1225.17 122.209C1222.32 119.567 1218.21 118.246 1212.84 118.246C1207.17 118.246 1202.67 119.482 1199.35 121.953C1196.07 124.425 1193.85 127.344 1192.7 130.71L1171.1 127.642C1172.8 121.676 1175.61 116.69 1179.53 112.685C1183.45 108.636 1188.25 105.611 1193.92 103.608C1199.58 101.562 1205.85 100.54 1212.71 100.54C1217.44 100.54 1222.15 101.094 1226.83 102.202C1231.52 103.31 1235.81 105.142 1239.68 107.699C1243.56 110.213 1246.67 113.643 1249.02 117.99C1251.4 122.337 1252.59 127.77 1252.59 134.29V200H1230.35V186.513H1229.58C1228.18 189.24 1226.2 191.797 1223.64 194.183C1221.12 196.527 1217.95 198.423 1214.11 199.872C1210.32 201.278 1205.87 201.982 1200.76 201.982ZM1206.76 184.979C1211.41 184.979 1215.44 184.062 1218.84 182.23C1222.25 180.355 1224.87 177.884 1226.71 174.815C1228.58 171.747 1229.52 168.402 1229.52 164.78V153.21C1228.8 153.807 1227.56 154.361 1225.81 154.872C1224.11 155.384 1222.19 155.831 1220.06 156.214C1217.93 156.598 1215.82 156.939 1213.73 157.237C1211.64 157.536 1209.83 157.791 1208.3 158.004C1204.85 158.473 1201.76 159.24 1199.03 160.305C1196.3 161.371 1194.15 162.862 1192.57 164.78C1191 166.655 1190.21 169.084 1190.21 172.067C1190.21 176.328 1191.76 179.545 1194.87 181.719C1197.99 183.892 1201.95 184.979 1206.76 184.979ZM1275.86 200V101.818H1299V200H1275.86ZM1287.5 87.8835C1283.83 87.8835 1280.68 86.669 1278.04 84.2401C1275.39 81.7685 1274.07 78.8068 1274.07 75.3551C1274.07 71.8608 1275.39 68.8991 1278.04 66.4702C1280.68 63.9986 1283.83 62.7628 1287.5 62.7628C1291.2 62.7628 1294.36 63.9986 1296.96 66.4702C1299.6 68.8991 1300.92 71.8608 1300.92 75.3551C1300.92 78.8068 1299.6 81.7685 1296.96 84.2401C1294.36 86.669 1291.2 87.8835 1287.5 87.8835ZM1345.93 142.472V200H1322.8V101.818H1344.91V118.501H1346.06C1348.32 113.004 1351.92 108.636 1356.87 105.398C1361.85 102.159 1368.01 100.54 1375.34 100.54C1382.11 100.54 1388.02 101.989 1393.04 104.886C1398.12 107.784 1402.04 111.982 1404.81 117.479C1407.62 122.976 1409 129.645 1408.96 137.486V200H1385.82V141.065C1385.82 134.503 1384.12 129.368 1380.71 125.661C1377.34 121.953 1372.67 120.099 1366.71 120.099C1362.66 120.099 1359.06 120.994 1355.91 122.784C1352.8 124.531 1350.35 127.067 1348.56 130.391C1346.81 133.714 1345.93 137.741 1345.93 142.472Z" fill="black"/>+<defs>+<pattern id="pattern0" patternContentUnits="objectBoundingBox" width="1" height="1">+<use xlink:href="#image0_2_74" transform="scale(0.00746269 0.00833333)"/>+</pattern>+<clipPath id="clip0_2_74">+<rect width="295" height="258" fill="white"/>+</clipPath>+<image id="image0_2_74" width="134" height="120" xlink:href="data:image/png;base64,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"/>+</defs>+</svg>diff --git a/docs/mint.json b/docs/mint.jsonnew file mode 100644index 000000000..21ce5a14d--- /dev/null+++ b/docs/mint.json@@ -0,0 +1,50 @@+{+ "$schema": "https://mintlify.com/schema.json",+ "name": "Embedchain",+ "logo": {+ "dark": "/logo/dark.svg",+ "light": "/logo/light.svg"+ },+ "favicon": "/favicon.png",+ "colors": {+ "primary": "#12A7D3",+ "light": "#81D7F7",+ "dark": "#004E7A"+ },+ "topbarLinks": [+ {+ "name": "Twitter",+ "url": "https://twitter.com/embedchain"+ },+ {+ "name": "Discord",+ "url": "https://discord.gg/6PzXDgEjG5"+ }+ ],+ "topbarCtaButton": {+ "name": "GitHub",+ "url": "https://embedchain.ai"+ },+ "navigation": [+ {+ "group": "Getting started",+ "pages": ["quickstart", "introduction"]+ },+ {+ "group": "Advanced",+ "pages": ["advanced/advanced_usage", "advanced/data_types", "advanced/query_configuration", "advanced/configuration", "advanced/testing", "advanced/showcase"]+ },+ {+ "group": "Contribution Guidelines",+ "pages": ["contribution/dev", "contribution/docs"]+ }++ ],+ "footerSocials": {+ "twitter": "https://twitter.com/embedchain",+ "github": "https://github.com/embedchain/embedchain",+ "linkedin": "https://www.linkedin.com/company/embedchain"+ },+ "backgroundImage": "/background.png",+ "isWhiteLabeled": true+}diff --git a/docs/quickstart.mdx b/docs/quickstart.mdxnew file mode 100644index 000000000..664f422e5--- /dev/null+++ b/docs/quickstart.mdx@@ -0,0 +1,29 @@+---+title: 'π Quickstart'+description: 'π‘ Start building LLM powered bots under 30 seconds'+---++Install embedchain python package:++```bash+pip install embedchain+```++Run your first bot in python using the following code. Make sure to set the `OPENAI_API_KEY` π environment variable in the code.++```python+import os++from embedchain Import App++os.environ["OPENAI_API_KEY"] = "xxx"+elon_musk_bot = App()++# Embed Online Resources+elon_musk_bot.add("web_page", "https://en.wikipedia.org/wiki/Elon_Musk")+elon_musk_bot.add("web_page", "https://www.tesla.com/elon-musk")++response = elon_bot.query("How many companies does Elon Musk run?")+print(response)+# Answer: 'Elon Musk runs four companies: Tesla, SpaceX, Neuralink, and The Boring Company.'+```