ocrcontext 0.1.4__tar.gz → 0.1.5__tar.gz

{ocrcontext-0.1.4 → ocrcontext-0.1.5}/CHANGELOG.md

@@ -7,6 +7,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.1.5] - 2026-06-27
+
+### Fixed
+- CLI now shows a clear error message when an LLM provider API key is missing
+  instead of a raw traceback (e.g. `OPENAI_API_KEY` not set).
+- CLI prints a first-run warning before the OCR step when PaddleOCR models
+  have not been downloaded yet, so users know the ~90 MB download is expected.
+
 ## [0.1.4] - 2026-06-27
 
 ### Added
@@ -95,7 +103,8 @@ into a standalone, LLM-agnostic library.
 - **Packaging** — optional extras `[paddle]`, `[trocr]`, `[vision]`, `[all]`;
   PEP 561 typed (`py.typed`); examples and a GPU/network-free test suite.
 
-[Unreleased]: https://github.com/bahadirkarsli/ocrcontext/compare/v0.1.4...HEAD
+[Unreleased]: https://github.com/bahadirkarsli/ocrcontext/compare/v0.1.5...HEAD
+[0.1.5]: https://github.com/bahadirkarsli/ocrcontext/compare/v0.1.4...v0.1.5
 [0.1.4]: https://github.com/bahadirkarsli/ocrcontext/compare/v0.1.3...v0.1.4
 [0.1.3]: https://github.com/bahadirkarsli/ocrcontext/compare/v0.1.2...v0.1.3
 [0.1.2]: https://github.com/bahadirkarsli/ocrcontext/compare/v0.1.1...v0.1.2

{ocrcontext-0.1.4 → ocrcontext-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocrcontext
-Version: 0.1.4
+Version: 0.1.5
 Summary: Decoupled, LLM-agnostic document OCR + structured extraction. Vision and LLM parsing in 3 lines of code.
 Project-URL: Homepage, https://github.com/BahadirKarsli/OCRContext
 Project-URL: Repository, https://github.com/BahadirKarsli/OCRContext

{ocrcontext-0.1.4 → ocrcontext-0.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ocrcontext"
-version = "0.1.4"
+version = "0.1.5"
 description = "Decoupled, LLM-agnostic document OCR + structured extraction. Vision and LLM parsing in 3 lines of code."
 readme = "README.md"
 license = { text = "MIT" }

{ocrcontext-0.1.4 → ocrcontext-0.1.5}/src/ocrcontext/cli.py

@@ -116,6 +116,13 @@ _SCHEMA_NAMES = list(_SCHEMAS)
 
 def _build_llm(provider: str, model: str):
     """Dynamically import the right LangChain provider class."""
+    _API_KEY_HINTS = {
+        "openai":    ("OPENAI_API_KEY",    "platform.openai.com/api-keys"),
+        "anthropic": ("ANTHROPIC_API_KEY", "console.anthropic.com/settings/keys"),
+        "google":    ("GOOGLE_API_KEY",    "aistudio.google.com/apikey"),
+        "ollama":    (None, None),
+    }
+
     try:
         if provider == "openai":
             from langchain_openai import ChatOpenAI  # type: ignore[import-untyped]
@@ -136,6 +143,19 @@ def _build_llm(provider: str, model: str):
             err=True,
         )
         raise typer.Exit(code=1)
+    except Exception as exc:
+        msg = str(exc)
+        if "api_key" in msg.lower() or "credentials" in msg.lower() or "auth" in msg.lower():
+            env_var, url = _API_KEY_HINTS.get(provider, (None, None))
+            hint = f"Set it with:  $env:{env_var} = \"...\"" if env_var else ""
+            url_hint = f"\nGet a key at: {url}" if url else ""
+            typer.echo(
+                f"[ERROR] No API key found for '{provider}'.\n{hint}{url_hint}",
+                err=True,
+            )
+        else:
+            typer.echo(f"[ERROR] Failed to initialize '{provider}': {exc}", err=True)
+        raise typer.Exit(code=1)
 
     typer.echo(
         f"[ERROR] Unknown provider '{provider}'. "
@@ -213,6 +233,11 @@ def extract(
 
     try:
         _info(f"file: {file_path.name}")
+
+        paddlex_cache = Path(os.environ.get("PADDLE_PDX_CACHE_HOME", Path.home() / ".paddlex"))
+        if not (paddlex_cache / "official_models").exists():
+            _info("first run: downloading OCR model (~90 MB), this may take a minute...")
+
         _info("OCR...")
 
         ocr_result = analyzer.analyze(