haiku.rag 0.7.2__tar.gz → 0.7.4__tar.gz

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/.gitignore

@@ -17,3 +17,4 @@ tests/data/
 
 # environment variables
 .env
+TODO.md

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.7.2
+Version: 0.7.4
 Summary: Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/docs/cli.md

@@ -2,6 +2,23 @@
 
 The `haiku-rag` CLI provides complete document management functionality.
 
+## Shell Autocompletion
+
+Enable shell autocompletion for faster, error‑free usage.
+
+- Temporary (current shell only):
+  ```bash
+  eval "$(haiku-rag --show-completion)"
+  ```
+- Permanent installation:
+  ```bash
+  haiku-rag --install-completion
+  ```
+
+What’s completed:
+- `get` and `delete`/`rm`: Document IDs from the selected database (respects `--db`).
+- `add-src`: Local filesystem paths (URLs can still be typed manually).
+
 ## Document Management
 
 ### List Documents
@@ -26,13 +43,16 @@ haiku-rag add-src https://example.com/article.html
 ### Get Document
 
 ```bash
-haiku-rag get 1
+haiku-rag get <TAB>
+# or
+haiku-rag get 3f4a...   # document ID (autocomplete supported)
 ```
 
 ### Delete Document
 
 ```bash
-haiku-rag delete 1
+haiku-rag delete <TAB>
+haiku-rag rm <TAB>       # alias
 ```
 
 ### Rebuild Database

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "haiku.rag"
-version = "0.7.2"
+version = "0.7.4"
 description = "Retrieval Augmented Generation (RAG) with LanceDB"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/src/haiku/rag/app.py

@@ -50,8 +50,13 @@ class HaikuRAGApp:
 
     async def delete_document(self, doc_id: str):
         async with HaikuRAG(db_path=self.db_path) as self.client:
-            await self.client.delete_document(doc_id)
-            self.console.print(f"[b]Document {doc_id} deleted successfully.[/b]")
+            deleted = await self.client.delete_document(doc_id)
+            if deleted:
+                self.console.print(f"[b]Document {doc_id} deleted successfully.[/b]")
+            else:
+                self.console.print(
+                    f"[yellow]Document with id {doc_id} not found.[/yellow]"
+                )
 
     async def search(self, query: str, limit: int = 5):
         async with HaikuRAG(db_path=self.db_path) as self.client:

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/src/haiku/rag/cli.py

@@ -8,6 +8,7 @@ from rich.console import Console
 
 from haiku.rag.app import HaikuRAGApp
 from haiku.rag.config import Config
+from haiku.rag.logging import configure_cli_logging
 from haiku.rag.migration import migrate_sqlite_to_lancedb
 from haiku.rag.utils import is_up_to_date
 
@@ -21,6 +22,65 @@ cli = typer.Typer(
 console = Console()
 
 
+def complete_document_ids(ctx: typer.Context, incomplete: str):
+    """Autocomplete document IDs from the selected DB."""
+    db_path = ctx.params.get("db") or (Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb")
+
+    try:
+        from haiku.rag.client import HaikuRAG
+
+        async def _list_ids():
+            async with HaikuRAG(db_path) as client:
+                docs = await client.list_documents()
+                return [d.id for d in docs if d.id]
+
+        ids = asyncio.run(_list_ids())
+    except Exception:
+        return []
+
+    return [i for i in ids if i and i.startswith(incomplete)]
+
+
+def complete_local_paths(ctx: typer.Context, incomplete: str) -> list[str]:
+    """Autocomplete local filesystem paths.
+
+    Provides directory/file suggestions based on the current incomplete input.
+    Does not validate or restrict to specific extensions to keep it flexible
+    (URLs are still allowed to be typed manually).
+    """
+    try:
+        text = incomplete or ""
+
+        # Expand user home
+        from os.path import expanduser
+
+        expanded = expanduser(text)
+        p = Path(expanded)
+
+        # Choose directory to list and prefix to filter
+        if text == "" or text.endswith(("/", "\\")):
+            directory = p
+            prefix = ""
+        else:
+            directory = p.parent
+            prefix = p.name
+
+        if not directory.exists():
+            return []
+
+        suggestions: list[str] = []
+        for entry in directory.iterdir():
+            name = entry.name
+            if not prefix or name.startswith(prefix):
+                suggestion = str(directory / name)
+                if entry.is_dir():
+                    suggestion += "/"
+                suggestions.append(suggestion)
+        return suggestions
+    except Exception:
+        return []
+
+
 async def check_version():
     """Check if haiku.rag is up to date and show warning if not."""
     up_to_date, current_version, latest_version = await is_up_to_date()
@@ -49,6 +109,8 @@ def main(
     ),
 ):
     """haiku.rag CLI - Vector database RAG system"""
+    # Ensure only haiku.rag logs are emitted in CLI context
+    configure_cli_logging()
     # Run version check before any command
     asyncio.run(check_version())
 
@@ -84,6 +146,7 @@ def add_document_text(
 def add_document_src(
     source: str = typer.Argument(
         help="The file path or URL of the document to add",
+        autocompletion=complete_local_paths,
     ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
@@ -99,6 +162,7 @@ def add_document_src(
 def get_document(
     doc_id: str = typer.Argument(
         help="The ID of the document to get",
+        autocompletion=complete_document_ids,
     ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
@@ -114,6 +178,7 @@ def get_document(
 def delete_document(
     doc_id: str = typer.Argument(
         help="The ID of the document to delete",
+        autocompletion=complete_document_ids,
     ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
@@ -125,6 +190,10 @@ def delete_document(
     asyncio.run(app.delete_document(doc_id=doc_id))
 
 
+# Add alias `rm` for delete
+cli.command("rm", help="Alias for delete: remove a document by its ID")(delete_document)
+
+
 @cli.command("search", help="Search for documents by a query")
 def search(
     query: str = typer.Argument(

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/src/haiku/rag/embeddings/base.py

@@ -9,7 +9,7 @@ class EmbedderBase:
         self._model = model
         self._vector_dim = vector_dim
 
-    async def embed(self, text: str) -> list[float]:
+    async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
         raise NotImplementedError(
             "Embedder is an abstract class. Please implement the embed method in a subclass."
         )

haiku_rag-0.7.4/src/haiku/rag/embeddings/ollama.py

@@ -0,0 +1,17 @@
+from openai import AsyncOpenAI
+
+from haiku.rag.config import Config
+from haiku.rag.embeddings.base import EmbedderBase
+
+
+class Embedder(EmbedderBase):
+    async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
+        client = AsyncOpenAI(base_url=f"{Config.OLLAMA_BASE_URL}/v1", api_key="dummy")
+        response = await client.embeddings.create(
+            model=self._model,
+            input=text,
+        )
+        if isinstance(text, str):
+            return response.data[0].embedding
+        else:
+            return [item.embedding for item in response.data]

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/src/haiku/rag/embeddings/openai.py

@@ -4,10 +4,13 @@ from haiku.rag.embeddings.base import EmbedderBase
 
 
 class Embedder(EmbedderBase):
-    async def embed(self, text: str) -> list[float]:
+    async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
         client = AsyncOpenAI()
         response = await client.embeddings.create(
             model=self._model,
             input=text,
         )
-        return response.data[0].embedding
+        if isinstance(text, str):
+            return response.data[0].embedding
+        else:
+            return [item.embedding for item in response.data]

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/src/haiku/rag/embeddings/vllm.py

@@ -5,7 +5,7 @@ from haiku.rag.embeddings.base import EmbedderBase
 
 
 class Embedder(EmbedderBase):
-    async def embed(self, text: str) -> list[float]:
+    async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
         client = AsyncOpenAI(
             base_url=f"{Config.VLLM_EMBEDDINGS_BASE_URL}/v1", api_key="dummy"
         )
@@ -13,4 +13,7 @@ class Embedder(EmbedderBase):
             model=self._model,
             input=text,
         )
-        return response.data[0].embedding
+        if isinstance(text, str):
+            return response.data[0].embedding
+        else:
+            return [item.embedding for item in response.data]

haiku_rag-0.7.4/src/haiku/rag/embeddings/voyageai.py

@@ -0,0 +1,17 @@
+try:
+    from voyageai.client import Client  # type: ignore
+
+    from haiku.rag.embeddings.base import EmbedderBase
+
+    class Embedder(EmbedderBase):
+        async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
+            client = Client()
+            if isinstance(text, str):
+                res = client.embed([text], model=self._model, output_dtype="float")
+                return res.embeddings[0]  # type: ignore[return-value]
+            else:
+                res = client.embed(text, model=self._model, output_dtype="float")
+                return res.embeddings  # type: ignore[return-value]
+
+except ImportError:
+    pass

haiku_rag-0.7.4/src/haiku/rag/logging.py

@@ -0,0 +1,53 @@
+import logging
+
+from rich.console import Console
+from rich.logging import RichHandler
+
+
+def get_logger() -> logging.Logger:
+    """Return the library logger configured with a Rich handler."""
+    logger = logging.getLogger("haiku.rag")
+
+    handler = RichHandler(
+        console=Console(stderr=True),
+        rich_tracebacks=True,
+    )
+    formatter = logging.Formatter("%(message)s")
+    handler.setFormatter(formatter)
+
+    logger.setLevel(logging.INFO)
+
+    # Remove any existing handlers to avoid duplicates on reconfiguration
+    for hdlr in logger.handlers[:]:
+        logger.removeHandler(hdlr)
+
+    logger.addHandler(handler)
+    # Do not let messages propagate to the root logger
+    logger.propagate = False
+    return logger
+
+
+def configure_cli_logging(level: int = logging.INFO) -> logging.Logger:
+    """Configure logging for CLI runs.
+
+    - Silence ALL non-haiku.rag loggers by detaching root handlers and setting
+      their level to ERROR.
+    - Attach a Rich handler only to the "haiku.rag" logger.
+    - Prevent propagation so only our logger prints in the CLI.
+    """
+    # Silence root logger completely
+    root = logging.getLogger()
+    for hdlr in root.handlers[:]:
+        root.removeHandler(hdlr)
+    root.setLevel(logging.ERROR)
+
+    # Optionally silence some commonly noisy libraries explicitly as a safeguard
+    for noisy in ("httpx", "httpcore", "docling", "urllib3", "asyncio"):
+        logging.getLogger(noisy).setLevel(logging.ERROR)
+        logging.getLogger(noisy).propagate = False
+
+    # Configure and return our app logger
+    logger = get_logger()
+    logger.setLevel(level)
+    logger.propagate = False
+    return logger

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/src/haiku/rag/store/repositories/chunk.py

@@ -154,13 +154,7 @@ class ChunkRepository:
         """Create chunks and embeddings for a document from DoclingDocument."""
         chunk_texts = await chunker.chunk(document)
 
-        # Generate embeddings in parallel for all chunks
-        embeddings_tasks = []
-        for chunk_text in chunk_texts:
-            embeddings_tasks.append(self.embedder.embed(chunk_text))
-
-        # Wait for all embeddings to complete
-        embeddings = await asyncio.gather(*embeddings_tasks)
+        embeddings = await self.embedder.embed(chunk_texts)
 
         # Prepare all chunk records for batch insertion
         chunk_records = []

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/tests/test_embedder.py

@@ -28,7 +28,13 @@ async def test_ollama_embedder():
         "Python is my favorite programming language.",
         "I love to travel and see new places.",
     ]
-    embeddings = [np.array(await embedder.embed(phrase)) for phrase in phrases]
+
+    # Test batch embedding
+    embeddings = await embedder.embed(phrases)
+    assert isinstance(embeddings, list)
+    assert len(embeddings) == 3
+    assert all(isinstance(emb, list) for emb in embeddings)
+    embeddings = [np.array(emb) for emb in embeddings]
 
     test_phrase = "I am going for a camping trip."
     test_embedding = await embedder.embed(test_phrase)
@@ -58,7 +64,13 @@ async def test_openai_embedder():
         "Python is my favorite programming language.",
         "I love to travel and see new places.",
     ]
-    embeddings = [np.array(await embedder.embed(phrase)) for phrase in phrases]
+
+    # Test batch embedding
+    embeddings = await embedder.embed(phrases)
+    assert isinstance(embeddings, list)
+    assert len(embeddings) == 3
+    assert all(isinstance(emb, list) for emb in embeddings)
+    embeddings = [np.array(emb) for emb in embeddings]
 
     test_phrase = "I am going for a camping trip."
     test_embedding = await embedder.embed(test_phrase)
@@ -91,7 +103,13 @@ async def test_voyageai_embedder():
             "Python is my favorite programming language.",
             "I love to travel and see new places.",
         ]
-        embeddings = [np.array(await embedder.embed(phrase)) for phrase in phrases]
+
+        # Test batch embedding
+        embeddings = await embedder.embed(phrases)
+        assert isinstance(embeddings, list)
+        assert len(embeddings) == 3
+        assert all(isinstance(emb, list) for emb in embeddings)
+        embeddings = [np.array(emb) for emb in embeddings]
 
         test_phrase = "I am going for a camping trip."
         test_embedding = await embedder.embed(test_phrase)
@@ -126,7 +144,13 @@ async def test_vllm_embedder():
         "Python is my favorite programming language.",
         "I love to travel and see new places.",
     ]
-    embeddings = [np.array(await embedder.embed(phrase)) for phrase in phrases]
+
+    # Test batch embedding
+    embeddings = await embedder.embed(phrases)
+    assert isinstance(embeddings, list)
+    assert len(embeddings) == 3
+    assert all(isinstance(emb, list) for emb in embeddings)
+    embeddings = [np.array(emb) for emb in embeddings]
 
     test_phrase = "I am going for a camping trip."
     test_embedding = await embedder.embed(test_phrase)

{haiku_rag-0.7.2 → haiku_rag-0.7.4}/uv.lock

@@ -951,7 +951,7 @@ wheels = [
 
 [[package]]
 name = "haiku-rag"
-version = "0.7.2"
+version = "0.7.4"
 source = { editable = "." }
 dependencies = [
     { name = "docling" },

haiku_rag-0.7.2/src/haiku/rag/embeddings/ollama.py

@@ -1,11 +0,0 @@
-from ollama import AsyncClient
-
-from haiku.rag.config import Config
-from haiku.rag.embeddings.base import EmbedderBase
-
-
-class Embedder(EmbedderBase):
-    async def embed(self, text: str) -> list[float]:
-        client = AsyncClient(host=Config.OLLAMA_BASE_URL)
-        res = await client.embeddings(model=self._model, prompt=text)
-        return list(res["embedding"])

haiku_rag-0.7.2/src/haiku/rag/embeddings/voyageai.py

@@ -1,13 +0,0 @@
-try:
-    from voyageai.client import Client  # type: ignore
-
-    from haiku.rag.embeddings.base import EmbedderBase
-
-    class Embedder(EmbedderBase):
-        async def embed(self, text: str) -> list[float]:
-            client = Client()
-            res = client.embed([text], model=self._model, output_dtype="float")
-            return res.embeddings[0]  # type: ignore[return-value]
-
-except ImportError:
-    pass

haiku_rag-0.7.2/src/haiku/rag/logging.py

@@ -1,29 +0,0 @@
-import logging
-
-from rich.console import Console
-from rich.logging import RichHandler
-
-logging.basicConfig(level=logging.DEBUG)
-logging.getLogger("httpx").setLevel(logging.WARNING)
-logging.getLogger("httpcore").setLevel(logging.WARNING)
-logging.getLogger("docling").setLevel(logging.WARNING)
-
-
-def get_logger() -> logging.Logger:
-    logger = logging.getLogger("haiku.rag")
-
-    handler = RichHandler(
-        console=Console(stderr=True),
-        rich_tracebacks=True,
-    )
-    formatter = logging.Formatter("%(message)s")
-    handler.setFormatter(formatter)
-
-    logger.setLevel("INFO")
-
-    # Remove any existing handlers to avoid duplicates on reconfiguration
-    for hdlr in logger.handlers[:]:
-        logger.removeHandler(hdlr)
-
-    logger.addHandler(handler)
-    return logger