klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[fix] dot file and docs (#1044)

Browse Source
This commit is contained in:
Sidharth Mohanty
2023-12-21 18:50:12 +05:30
committed by GitHub
parent b77d9d750f
commit ec8549d0e1
7 changed files with 57 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
docs/deployment/embedchain_ai.mdx Normal file
View File

@@ -0,0 +1,38 @@
---
title: 'Embedchain.ai'
description: 'Deploy your RAG application to embedchain.ai platform'
---
## Deploy on Embedchain Platform
Embedchain enables developers to deploy their LLM-powered apps in production using the [Embedchain platform](https://app.embedchain.ai). The platform offers free access to context on your data through its REST API. Once the pipeline is deployed, you can update your data sources anytime after deployment.
See the example below on how to use the deploy your app (for free):
```python
from embedchain import Pipeline as App
# Initialize app
app = App()
# Add data source
app.add("https://www.forbes.com/profile/elon-musk")
# Deploy your pipeline to Embedchain Platform
app.deploy()
# 🔑 Enter your Embedchain API key. You can find the API key at https://app.embedchain.ai/settings/keys/
# ec-xxxxxx
# 🛠️ Creating pipeline on the platform...
# 🎉🎉🎉 Pipeline created successfully! View your pipeline: https://app.embedchain.ai/pipelines/xxxxx
# 🛠️ Adding data to your pipeline...
# ✅ Data of type: web_page, value: https://www.forbes.com/profile/elon-musk added successfully.
```
## Seeking help?
If you run into issues with deployment, please feel free to reach out to us via any of the following methods:
<Snippet file="get-help.mdx" />

30
docs/get-started/deployment.mdx
View File

@@ -10,38 +10,10 @@ After successfully setting up and testing your RAG app locally, the next step is
<Card title="Modal.com" href="/deployment/modal_com"></Card>
<Card title="Render.com" href="/deployment/render_com"></Card>
<Card title="Streamlit.io" href="/deployment/streamlit_io"></Card>
<Card title="Embedchain Platform" href="#option-1-deploy-on-embedchain-platform"></Card>
<Card title="Embedchain.ai" href="/deployment/embedchain_ai"></Card>
<Card title="Self-hosting" href="#option-2-self-hosting"></Card>
</CardGroup>
## Deploy on Embedchain Platform
Embedchain enables developers to deploy their LLM-powered apps in production using the [Embedchain platform](https://app.embedchain.ai). The platform offers free access to context on your data through its REST API. Once the pipeline is deployed, you can update your data sources anytime after deployment.
See the example below on how to use the deploy your app (for free):
```python
from embedchain import Pipeline as App
# Initialize app
app = App()
# Add data source
app.add("https://www.forbes.com/profile/elon-musk")
# Deploy your pipeline to Embedchain Platform
app.deploy()
# 🔑 Enter your Embedchain API key. You can find the API key at https://app.embedchain.ai/settings/keys/
# ec-xxxxxx
# 🛠️ Creating pipeline on the platform...
# 🎉🎉🎉 Pipeline created successfully! View your pipeline: https://app.embedchain.ai/pipelines/xxxxx
# 🛠️ Adding data to your pipeline...
# ✅ Data of type: web_page, value: https://www.forbes.com/profile/elon-musk added successfully.
```
## Self-hosting
You can also deploy Embedchain as a self-hosted service using the dockerized REST API service that we provide. Please follow the [guide here](/examples/rest-api) on how to use the REST API service. Here are some tutorials on how to deploy a containerized application to different platforms like AWS, GCP, Azure etc:

17
docs/get-started/quickstart.mdx
View File

@@ -65,21 +65,4 @@ Creating an app involves 3 steps:
To learn about other features, click [here](https://docs.embedchain.ai/get-started/introduction)
</Accordion>
</Step>
<Step title="🚀 Seamlessly launch your App on the Embedchain Platform!">
```python
app.deploy()
# 🔑 Enter your Embedchain API key. You can find the API key at https://app.embedchain.ai/settings/keys/
# ec-xxxxxx
# 🛠️ Creating pipeline on the platform...
# 🎉🎉🎉 Pipeline created successfully! View your pipeline: https://app.embedchain.ai/pipelines/xxxxx
# 🛠️ Adding data to your pipeline...
# ✅ Data of type: web_page, value: https://www.forbes.com/profile/elon-musk added successfully.
```
<Accordion title="Share your app with others" icon="laptop-mobile">
You can now share your app with others from our platform.
Access your app on our [platform](https://app.embedchain.ai/).
</Accordion>
</Step>
</Steps>

3
docs/mint.json
View File

@@ -90,7 +90,8 @@
"deployment/fly_io",
"deployment/modal_com",
"deployment/render_com",
"deployment/streamlit_io"
"deployment/streamlit_io",
"deployment/embedchain_ai"
]
},
{

3
embedchain/loaders/directory_loader.py
View File

@@ -38,6 +38,9 @@ class DirectoryLoader(BaseLoader):
def _process_directory(self, directory_path: Path):
data_list = []
for file_path in directory_path.rglob("*") if self.recursive else directory_path.glob("*"):
# don't include dotfiles
if file_path.name.startswith("."):
continue
if file_path.is_file() and (not self.extensions or any(file_path.suffix == ext for ext in self.extensions)):
loader = self._predict_loader(file_path)
data_list.extend(loader.load_data(str(file_path))["data"])

16
examples/unacademy-ai/app.py
View File

@@ -1,9 +1,11 @@
import queue
import streamlit as st
from embedchain import Pipeline as App
from embedchain.config import BaseLlmConfig
from embedchain.helpers.callbacks import StreamingStdOutCallbackHandlerYield, generate
from embedchain.helpers.callbacks import (StreamingStdOutCallbackHandlerYield,
generate)
@st.cache_resource
@@ -19,7 +21,9 @@ assistant_avatar_url = "https://cdn-images-1.medium.com/v2/resize:fit:1200/1*LdF
st.markdown(f"# <img src='{assistant_avatar_url}' width={35} /> Unacademy UPSC AI", unsafe_allow_html=True)
styled_caption = """
<p style="font-size: 17px; color: #aaa;">🚀 An <a href="https://github.com/embedchain/embedchain">Embedchain</a> app powered with Unacademy\'s UPSC data!</p>
<p style="font-size: 17px; color: #aaa;">
🚀 An <a href="https://github.com/embedchain/embedchain">Embedchain</a> app powered with Unacademy\'s UPSC data!
</p>
"""
st.markdown(styled_caption, unsafe_allow_html=True)
@@ -33,7 +37,10 @@ with st.expander(":grey[Want to create your own Unacademy UPSC AI?]"):
```python
from embedchain import Pipeline as App
unacademy_ai_app = App()
unacademy_ai_app.add("https://unacademy.com/content/upsc/study-material/plan-policy/atma-nirbhar-bharat-3-0/", data_type="web_page")
unacademy_ai_app.add(
"https://unacademy.com/content/upsc/study-material/plan-policy/atma-nirbhar-bharat-3-0/",
data_type="web_page"
)
unacademy_ai_app.chat("What is Atma Nirbhar 3.0?")
```
@@ -45,7 +52,8 @@ if "messages" not in st.session_state:
st.session_state.messages = [
{
"role": "assistant",
"content": """Hi, I'm Unacademy UPSC AI bot, who can answer any questions related to UPSC preparation. Let me help you prepare better for UPSC.\n
"content": """Hi, I'm Unacademy UPSC AI bot, who can answer any questions related to UPSC preparation.
Let me help you prepare better for UPSC.\n
Sample questions:
- What are the subjects in UPSC CSE?
- What is the CSE scholarship price amount?

2
pyproject.toml
View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "embedchain"
version = "0.1.38"
version = "0.1.39"
description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
authors = [
"Taranjeet Singh <taranjeet@embedchain.ai>",