Deploy remaining bots and fix schema validation (#927)

This commit is contained in:
Sidharth Mohanty
2023-11-10 00:14:47 +05:30
committed by GitHub
parent 0d568c758b
commit 14712cac88
13 changed files with 110 additions and 26 deletions

View File

@@ -1,7 +1,7 @@
app:
config:
id: 'my-app'
log_level: 'WARN'
log_level: 'WARNING'
collect_metrics: true
collection_name: 'my-app'
@@ -30,4 +30,4 @@ embedder:
provider: openai
config:
model: 'text-embedding-ada-002'
deployment_name: null
deployment_name: 'my-app'

View File

@@ -1,21 +1,46 @@
---
title: '📱 Telegram Bot'
title: "📱 Telegram Bot"
---
### 🖼️ Template Setup
- Fork [this](https://replit.com/@taranjeetio/EC-Telegram-Bot-Template?v=1#README.md) replit template.
- Set your `OPENAI_API_KEY` in Secrets.
- Open the Telegram app and search for the `BotFather` user.
- Start a chat with BotFather and use the `/newbot` command to create a new bot.
- Follow the instructions to choose a name and username for your bot.
- Once the bot is created, BotFather will provide you with a unique token for your bot.
- Set this token as `TELEGRAM_BOT_TOKEN` in Secrets.
<Tabs>
<Tab title="docker">
```bash
docker run --name telegram-bot -e OPENAI_API_KEY=sk-xxx -e TELEGRAM_BOT_TOKEN=xxx -p 8000:8000 embedchain/telegram-bot
```
<Note>
If you wish to use **Docker**, you would need to host your bot on a server.
You can use [ngrok](https://ngrok.com/) to expose your localhost to the
internet and then set the webhook using the ngrok URL.
</Note>
</Tab>
<Tab title="replit">
<Card>
Fork <ins>**[this](https://replit.com/@taranjeetio/EC-Telegram-Bot-Template?v=1#README.md)**</ins> replit template.
</Card>
- Set your `OPENAI_API_KEY` in Secrets.
- Set the unique token as `TELEGRAM_BOT_TOKEN` in Secrets.
</Tab>
</Tabs>
- Click on `Run` in the replit container and a URL will get generated for your bot.
- Now set your webhook by running the following link in your browser:
```url
https://api.telegram.org/bot<Your_Telegram_Bot_Token>/setWebhook?url=<Replit_Generated_URL>
```
- When you get a successful response in your browser, your bot is ready to be used.
### 🚀 Usage Instructions

View File

@@ -12,10 +12,19 @@ pip install --upgrade embedchain
2. Launch your WhatsApp bot:
<Tabs>
<Tab title="docker">
```bash
docker run --name whatsapp-bot -e OPENAI_API_KEY=sk-xxx -p 8000:8000 embedchain/whatsapp-bot
```
</Tab>
<Tab title="python">
```bash
python -m embedchain.bots.whatsapp --port 5000
```
</Tab>
</Tabs>
```bash
python -m embedchain.bots.whatsapp --port 5000
```
If your bot needs to be accessible online, use your machine's public IP or DNS. Otherwise, employ a proxy server like [ngrok](https://ngrok.com/) to make your local bot accessible.

View File

@@ -138,8 +138,7 @@ def detect_datatype(source: Any) -> DataType:
formatted_source = format_source(str(source), 30)
if url:
from langchain.document_loaders.youtube import \
ALLOWED_NETLOCK as YOUTUBE_ALLOWED_NETLOCS
from langchain.document_loaders.youtube import ALLOWED_NETLOCK as YOUTUBE_ALLOWED_NETLOCS
if url.netloc in YOUTUBE_ALLOWED_NETLOCS:
logging.debug(f"Source of `{formatted_source}` detected as `youtube_video`.")
@@ -309,7 +308,7 @@ def validate_yaml_config(config_data):
"gpt4all",
"jina",
"llama2",
"vertex_ai",
"vertexai",
),
Optional("config"): {
Optional("model"): str,
@@ -329,23 +328,17 @@ def validate_yaml_config(config_data):
Optional("provider"): Or(
"chroma", "elasticsearch", "opensearch", "pinecone", "qdrant", "weaviate", "zilliz"
),
Optional("config"): {
Optional("collection_name"): str,
Optional("dir"): str,
Optional("allow_reset"): bool,
Optional("host"): str,
Optional("port"): str,
},
Optional("config"): object, # TODO: add particular config schema for each provider
},
Optional("embedder"): {
Optional("provider"): Or("openai", "gpt4all", "huggingface", "vertexai"),
Optional("provider"): Or("openai", "gpt4all", "huggingface", "vertexai", "azure_openai"),
Optional("config"): {
Optional("model"): Optional(str),
Optional("deployment_name"): Optional(str),
},
},
Optional("embedding_model"): {
Optional("provider"): Or("openai", "gpt4all", "huggingface", "vertexai"),
Optional("provider"): Or("openai", "gpt4all", "huggingface", "vertexai", "azure_openai"),
Optional("config"): {
Optional("model"): str,
Optional("deployment_name"): str,

View File

@@ -0,0 +1,2 @@
TELEGRAM_BOT_TOKEN=
OPENAI_API_KEY=

View File

@@ -0,0 +1,11 @@
FROM python:3.11-slim
WORKDIR /usr/src/
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 8000
CMD ["python", "telegram_bot.py"]

View File

@@ -63,4 +63,4 @@ def send_message(chat_id, text):
if __name__ == "__main__":
app.run(host="0.0.0.0", port=5000, debug=False)
app.run(host="0.0.0.0", port=8000, debug=False)

View File

@@ -1,2 +0,0 @@
TELEGRAM_BOT_TOKEN=""
OPENAI_API_KEY=""

View File

@@ -0,0 +1 @@
OPENAI_API_KEY=

View File

@@ -0,0 +1,11 @@
FROM python:3.11-slim
WORKDIR /usr/src/
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 8000
CMD ["python", "whatsapp_bot.py"]

View File

@@ -1 +0,0 @@
OPENAI_API_KEY=""

View File

@@ -48,4 +48,4 @@ def query(message):
if __name__ == "__main__":
app.run(host="0.0.0.0", port=5000, debug=False)
app.run(host="0.0.0.0", port=8000, debug=False)

35
tests/test_utils.py Normal file
View File

@@ -0,0 +1,35 @@
import yaml
from embedchain.utils import validate_yaml_config
CONFIG_YAMLS = [
"configs/anthropic.yaml",
"configs/azure_openai.yaml",
"configs/chroma.yaml",
"configs/chunker.yaml",
"configs/cohere.yaml",
"configs/full-stack.yaml",
"configs/gpt4all.yaml",
"configs/huggingface.yaml",
"configs/jina.yaml",
"configs/llama2.yaml",
"configs/opensearch.yaml",
"configs/opensource.yaml",
"configs/pinecone.yaml",
"configs/vertexai.yaml",
"configs/weaviate.yaml",
]
class TestAllConfigYamls:
def test_all_config_yamls(self):
"""Test that all config yamls are valid."""
for config_yaml in CONFIG_YAMLS:
with open(config_yaml, "r") as f:
config = yaml.safe_load(f)
assert config is not None
try:
validate_yaml_config(config)
except Exception as e:
print(f"Error in {config_yaml}: {e}")
raise e