[Docs] add docs for youtube channel (#1072)

Co-authored-by: Deven Patel <deven298@yahoo.com>
This commit is contained in:
Deven Patel
2023-12-28 21:08:48 +05:30
committed by GitHub
parent 7a026ea282
commit 12e6eaf802
6 changed files with 26 additions and 8 deletions

View File

@@ -8,6 +8,7 @@ Embedchain comes with built-in support for various data sources. We handle the c
<Card title="📰 PDF file" href="/components/data-sources/pdf-file"></Card>
<Card title="📊 CSV file" href="/components/data-sources/csv"></Card>
<Card title="📃 JSON file" href="/components/data-sources/json"></Card>
<Card title="📽️ Youtube Channel" href="/components/data-sources/youtube-channel"></Card>
<Card title="📺 Youtube" href="/components/data-sources/youtube-video"></Card>
<Card title="📝 Text" href="/components/data-sources/text"></Card>
<Card title="📚 Documentation website" href="/components/data-sources/docs-site"></Card>

View File

@@ -0,0 +1,20 @@
---
title: '📽️ Youtube Channel'
---
To add all the videos from a youtube channel to your app, use the data_type as `youtube_channel`.
<Note>
Make sure you have all the required packages installed before using this data type. You can install them by running the following command in your terminal.
```bash
pip install -u "embedchain[youtube]"
```
</Note>
```python
from embedchain import Pipeline as App
app = App()
app.add("@channel_name", data_type="youtube_channel")
```

View File

@@ -2,8 +2,7 @@
title: '📺 Youtube'
---
To add any youtube video to your app, use the data_type (first argument to `.add()` method) as `youtube_video`. Eg:
To add any youtube video to your app, use the data_type as `youtube_video`. Eg:
```python
from embedchain import Pipeline as App

View File

@@ -189,8 +189,7 @@ class EmbedChain(JSONSerializable):
data_type = detect_datatype(source)
# `source_hash` is the md5 hash of the source argument
hash_object = hashlib.md5(str(source).encode("utf-8"))
source_hash = hash_object.hexdigest()
source_hash = hashlib.md5(str(source).encode("utf-8")).hexdigest()
self.user_asks.append([source, data_type.value, metadata])

View File

@@ -27,6 +27,7 @@ class DirectoryLoader(BaseLoader):
if not directory_path.is_dir():
raise ValueError(f"Invalid path: {path}")
logging.info(f"Loading data from directory: {path}")
data_list = self._process_directory(directory_path)
doc_id = hashlib.sha256((str(data_list) + str(directory_path)).encode()).hexdigest()
@@ -44,6 +45,8 @@ class DirectoryLoader(BaseLoader):
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"])
elif file_path.is_dir():
logging.info(f"Loading data from directory: {file_path}")
return data_list
def _predict_loader(self, file_path: Path) -> BaseLoader:

View File

@@ -358,10 +358,6 @@ def is_valid_json_string(source: str):
_ = json.loads(source)
return True
except json.JSONDecodeError:
logging.error(
"Insert valid string format of JSON. \
Check the docs to see the supported formats - `https://docs.embedchain.ai/data-sources/json`"
)
return False