[Improvements] improve package ux (#950)

Co-authored-by: Deven Patel <deven298@yahoo.com>

configs/gpt4.yaml

@@ -0,0 +1,8 @@
+llm:
+  provider: openai
+  config:
+    model: 'gpt-4'
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false

docs/get-started/quickstart.mdx

@@ -83,3 +83,9 @@ app.deploy()
 # 🛠️ Adding data to your pipeline...
 # ✅ Data of type: web_page, value: https://www.forbes.com/profile/elon-musk added successfully.
 ```
+
+You can try it out yourself using the following Google Colab notebook:
+
+<a href="https://colab.research.google.com/drive/17ON1LPonnXAtLaZEebnOktstB_1cJJmh?usp=sharing">
+    <img src="https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667" alt="Open in Colab" />
+</a>

embedchain/loaders/discourse.py

@@ -30,7 +30,7 @@ class DiscourseLoader(BaseLoader):
             )
 
     def _load_post(self, post_id):
-        post_url = f"{self.domain}/posts/{post_id}.json"
+        post_url = f"{self.domain}posts/{post_id}.json"
         response = requests.get(post_url)
         response.raise_for_status()
         response_data = response.json()
@@ -53,7 +53,7 @@ class DiscourseLoader(BaseLoader):
         data = []
         data_contents = []
         logging.info(f"Searching data on discourse url: {self.domain}, for query: {query}")
-        search_url = f"{self.domain}/search.json?q={query}"
+        search_url = f"{self.domain}search.json?q={query}"
         response = requests.get(search_url)
         response.raise_for_status()
         response_data = response.json()

embedchain/loaders/unstructured_file.py

@@ -4,7 +4,7 @@ try:
     from langchain.document_loaders import UnstructuredFileLoader
 except ImportError:
     raise ImportError(
-        'PDF File requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+        'Unstructured file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.1.10"
+version = "0.1.11"
 description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
 authors = [
     "Taranjeet Singh <taranjeet@embedchain.ai>",

tests/loaders/test_discourse.py

@@ -7,7 +7,7 @@ from embedchain.loaders.discourse import DiscourseLoader
 @pytest.fixture
 def discourse_loader_config():
     return {
-        "domain": "https://example.com",
+        "domain": "https://example.com/",
     }
 
 
@@ -17,9 +17,9 @@ def discourse_loader(discourse_loader_config):
 
 
 def test_discourse_loader_init_with_valid_config():
-    config = {"domain": "https://example.com"}
+    config = {"domain": "https://example.com/"}
     loader = DiscourseLoader(config=config)
-    assert loader.domain == "https://example.com"
+    assert loader.domain == "https://example.com/"
 
 
 def test_discourse_loader_init_with_missing_config():

tests/test_utils.py

@@ -9,6 +9,7 @@ CONFIG_YAMLS = [
     "configs/chunker.yaml",
     "configs/cohere.yaml",
     "configs/full-stack.yaml",
+    "configs/gpt4.yaml",
     "configs/gpt4all.yaml",
     "configs/huggingface.yaml",
     "configs/jina.yaml",
@@ -21,8 +22,7 @@ CONFIG_YAMLS = [
 ]
 
 
-class TestAllConfigYamls:
+def test_all_config_yamls():
-    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: