check if outputs already available, unzip them if yes

app.py

@@ -17,37 +17,44 @@ ChatHistory = list[list[Optional[str], Optional[str]]]
 
 # Because this is a one-click deploy app, we will be relying on env. variables being set
 openai_api_key = os.getenv("OPENAI_API_KEY")  # Mandatory for app to work
-readthedocs_url = os.getenv("READTHEDOCS_URL")  # Mandatory for app to work as intended
-readthedocs_version = os.getenv("READTHEDOCS_VERSION")
 
-if openai_api_key is None:
-    print(
-        "Warning: No OPENAI_API_KEY detected. Set it with 'export OPENAI_API_KEY=sk-...'."
-    )
 
-if readthedocs_url is None:
-    raise ValueError(
-        "No READTHEDOCS_URL detected. Set it with e.g. 'export READTHEDOCS_URL=https://orion.readthedocs.io/'"
-    )
+if os.path.exists("outputs.zip"):
+    print("Found outputs.zip, Skipping crawl and embed.")
+    extract_zip("outputs.zip", output_path="outputs")
+
+else:
+    readthedocs_url = os.getenv("READTHEDOCS_URL")  # Mandatory for app to work as intended
+    readthedocs_version = os.getenv("READTHEDOCS_VERSION")
 
-if readthedocs_version is None:
-    print(
+    if openai_api_key is None:
+        print(
+            "Warning: No OPENAI_API_KEY detected. Set it with 'export OPENAI_API_KEY=sk-...'."
+        )
+
+    if readthedocs_url is None:
+        raise ValueError(
+            "No READTHEDOCS_URL detected. Set it with e.g. 'export READTHEDOCS_URL=https://orion.readthedocs.io/'"
+        )
+
+    if readthedocs_version is None:
+        print(
+            """
+        Warning: No READTHEDOCS_VERSION detected. If multiple versions of the docs exist, they will all be scraped.
+        Set it with e.g. 'export READTHEDOCS_VERSION=en/stable'
         """
-    Warning: No READTHEDOCS_VERSION detected. If multiple versions of the docs exist, they will all be scraped.
-    Set it with e.g. 'export READTHEDOCS_VERSION=en/stable'
-    """
-    )
+        )
 
 
 # Override to put it anywhere
 save_directory = "outputs/"
 
-# scrape and embed content from readthedocs website
-embed_documents(
-    homepage_url=readthedocs_url,
-    save_directory=save_directory,
-    target_version=readthedocs_version,
-)
+    # scrape and embed content from readthedocs website
+    crawl_and_embed_docs(
+        homepage_url=readthedocs_url,
+        save_directory="outputs",  # Expected to be in outputs/ by buster cfg
+        target_version=readthedocs_version,
+    )
 
 # Setup RAG agent
 buster = setup_buster(cfg.buster_cfg)