rlmgrep 0.1.4__tar.gz → 0.1.5__tar.gz

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

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rlmgrep
-Version: 0.1.4
+Version: 0.1.5
 Summary: Grep-shaped CLI search powered by DSPy RLM
 Author: rlmgrep
 License: MIT
@@ -62,8 +62,6 @@ rlmgrep [options] "query" [paths...]
 Common options:
 
 - `-n` show line numbers (default)
-- `--no-line-number` hide line numbers
-- `-H` always show filenames (default)
 - `-C N` context lines before/after (grep-style)
 - `-A N` context lines after
 - `-B N` context lines before
@@ -120,7 +118,7 @@ rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
   - `1` = no matches
   - `2` = usage/config/error
 
-Agent tip: use `-n -H` and no context for parse-friendly output, then key off exit codes.
+Agent tip: use `-n` and no context for parse-friendly output, then key off exit codes.
 
 ## Regex-style queries (best effort)
 
@@ -160,7 +158,7 @@ file_hard_max = 1000
 # markitdown_image_llm_api_base = ""
 # markitdown_image_llm_prompt = ""
 # markitdown_enable_audio = false
-# markitdown_audio_model = "gpt-4o-mini-transcribe"
+# markitdown_audio_model = "gpt-4o-mini-transcribe-2025-12-15"
 # markitdown_audio_provider = "openai"
 # markitdown_audio_api_key = ""
 # markitdown_audio_api_base = ""
@@ -180,7 +178,7 @@ If more than one provider key is set and the model does not make the provider ob
 ## Non-text files (PDF, images, audio)
 
 - PDF files are parsed with `pypdf`. Each page gets a marker line `===== Page N =====`, and output lines include a `page=N` suffix.
-- Images and audio are converted via `markitdown` when enabled in config. For image/audio conversion, an `openai` Python client is required.
+- Images and audio are converted via `markitdown` when enabled in config. Image conversion supports `openai`, `anthropic`, and `gemini` providers; audio conversion currently supports `openai` only.
 - Converted image/audio text is cached in sidecar files named `<original>.<ext>.md` next to the original file and reused on subsequent runs.
 - Use `-a/--text` to force binary files to be read as text (UTF-8 with replacement).
 
@@ -188,7 +186,7 @@ If more than one provider key is set and the model does not make the provider ob
 
 - Prefer narrow corpora (globs/types) to reduce token usage.
 - Use `--max-llm-calls` to cap costs; combine with small `--max-iterations` for safety.
-- For reproducible parsing, use `-n -H` and avoid context (`-C/-A/-B`).
+- For reproducible parsing, use `-n` and avoid context (`-C/-A/-B`).
   
 ## Development
 

{rlmgrep-0.1.4 → rlmgrep-0.1.5}/README.md

@@ -50,8 +50,6 @@ rlmgrep [options] "query" [paths...]
 Common options:
 
 - `-n` show line numbers (default)
-- `--no-line-number` hide line numbers
-- `-H` always show filenames (default)
 - `-C N` context lines before/after (grep-style)
 - `-A N` context lines after
 - `-B N` context lines before
@@ -108,7 +106,7 @@ rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
   - `1` = no matches
   - `2` = usage/config/error
 
-Agent tip: use `-n -H` and no context for parse-friendly output, then key off exit codes.
+Agent tip: use `-n` and no context for parse-friendly output, then key off exit codes.
 
 ## Regex-style queries (best effort)
 
@@ -148,7 +146,7 @@ file_hard_max = 1000
 # markitdown_image_llm_api_base = ""
 # markitdown_image_llm_prompt = ""
 # markitdown_enable_audio = false
-# markitdown_audio_model = "gpt-4o-mini-transcribe"
+# markitdown_audio_model = "gpt-4o-mini-transcribe-2025-12-15"
 # markitdown_audio_provider = "openai"
 # markitdown_audio_api_key = ""
 # markitdown_audio_api_base = ""
@@ -168,7 +166,7 @@ If more than one provider key is set and the model does not make the provider ob
 ## Non-text files (PDF, images, audio)
 
 - PDF files are parsed with `pypdf`. Each page gets a marker line `===== Page N =====`, and output lines include a `page=N` suffix.
-- Images and audio are converted via `markitdown` when enabled in config. For image/audio conversion, an `openai` Python client is required.
+- Images and audio are converted via `markitdown` when enabled in config. Image conversion supports `openai`, `anthropic`, and `gemini` providers; audio conversion currently supports `openai` only.
 - Converted image/audio text is cached in sidecar files named `<original>.<ext>.md` next to the original file and reused on subsequent runs.
 - Use `-a/--text` to force binary files to be read as text (UTF-8 with replacement).
 
@@ -176,7 +174,7 @@ If more than one provider key is set and the model does not make the provider ob
 
 - Prefer narrow corpora (globs/types) to reduce token usage.
 - Use `--max-llm-calls` to cap costs; combine with small `--max-iterations` for safety.
-- For reproducible parsing, use `-n -H` and avoid context (`-C/-A/-B`).
+- For reproducible parsing, use `-n` and avoid context (`-C/-A/-B`).
   
 ## Development
 

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

@@ -1,6 +1,6 @@
 [project]
 name = "rlmgrep"
-version = "0.1.4"
+version = "0.1.5"
 description = "Grep-shaped CLI search powered by DSPy RLM"
 readme = "README.md"
 requires-python = ">=3.11"

{rlmgrep-0.1.4 → rlmgrep-0.1.5}/rlmgrep/__init__.py

@@ -1,2 +1,2 @@
 __all__ = ["__version__"]
-__version__ = "0.1.4"
+__version__ = "0.1.5"

{rlmgrep-0.1.4 → rlmgrep-0.1.5}/rlmgrep/cli.py

@@ -73,8 +73,6 @@ def _parse_args(argv: list[str]) -> argparse.Namespace:
     parser.add_argument("paths", nargs="*", help="Files or directories")
 
     parser.add_argument("-n", dest="line_numbers", action="store_true", help="Show line numbers (default)")
-    parser.add_argument("--no-line-number", dest="line_numbers", action="store_false", help="Hide line numbers")
-    parser.add_argument("-H", dest="with_filename", action="store_true", help="Always show filenames (default)")
     parser.add_argument("-r", dest="recursive", action="store_true", help="Recursive (directories are searched recursively by default)")
     parser.add_argument("--no-recursive", dest="recursive", action="store_false", help="Do not recurse directories")
     parser.set_defaults(recursive=True, line_numbers=True)
@@ -240,6 +238,33 @@ def _build_markitdown(config: dict, warnings: list[str]):
             kwargs["base_url"] = api_base
         return OpenAI(**kwargs)
 
+    class _LiteLLMClient:
+        def __init__(self, api_key: str | None, api_base: str | None):
+            try:
+                import litellm  # type: ignore
+            except Exception as exc:
+                raise RuntimeError("litellm not available") from exc
+            self._litellm = litellm
+            self._api_key = api_key
+            self._api_base = api_base
+            self.chat = self._Chat(self)
+
+        class _Chat:
+            def __init__(self, parent):
+                self.completions = parent._Completions(parent)
+
+        class _Completions:
+            def __init__(self, parent):
+                self._parent = parent
+
+            def create(self, model: str, messages):
+                kwargs = {"model": model, "messages": messages}
+                if self._parent._api_key:
+                    kwargs["api_key"] = self._parent._api_key
+                if self._parent._api_base:
+                    kwargs["api_base"] = self._parent._api_base
+                return self._parent._litellm.completion(**kwargs)
+
     llm_client = None
     if enable_images:
         if not llm_model:
@@ -247,18 +272,27 @@ def _build_markitdown(config: dict, warnings: list[str]):
                 "markitdown_enable_images set but markitdown_image_llm_model missing; skipping images"
             )
             enable_images = False
-        elif llm_provider != "openai":
-            warnings.append(
-                f"markitdown image LLM provider '{llm_provider}' not supported; skipping images"
-            )
-            enable_images = False
         else:
-            llm_client = _openai_client(
-                llm_api_key,
-                llm_api_base,
-                "openai package missing; skipping image conversion",
-            )
-            if llm_client is None:
+            if llm_provider == "openai":
+                llm_client = _openai_client(
+                    llm_api_key,
+                    llm_api_base,
+                    "openai package missing; skipping image conversion",
+                )
+                if llm_client is None:
+                    enable_images = False
+            elif llm_provider in {"gemini", "anthropic"}:
+                try:
+                    llm_client = _LiteLLMClient(llm_api_key, llm_api_base)
+                except RuntimeError:
+                    warnings.append(
+                        "litellm not available; skipping image conversion"
+                    )
+                    enable_images = False
+            else:
+                warnings.append(
+                    f"markitdown image LLM provider '{llm_provider}' not supported; skipping images"
+                )
                 enable_images = False
 
     md_kwargs: dict[str, object] = {"enable_plugins": False}

{rlmgrep-0.1.4 → rlmgrep-0.1.5}/rlmgrep/config.py

@@ -25,7 +25,7 @@ DEFAULT_CONFIG_TEXT = "\n".join(
         "# markitdown_image_llm_api_base = \"\"",
         "# markitdown_image_llm_prompt = \"\"",
         "# markitdown_enable_audio = false",
-        "# markitdown_audio_model = \"gpt-4o-mini-transcribe\"",
+        "# markitdown_audio_model = \"gpt-4o-mini-transcribe-2025-12-15\"",
         "# markitdown_audio_provider = \"openai\"",
         "# markitdown_audio_api_key = \"\"",
         "# markitdown_audio_api_base = \"\"",

{rlmgrep-0.1.4 → rlmgrep-0.1.5}/rlmgrep/render.py

@@ -28,11 +28,11 @@ def _format_line(
     heading: bool,
 ) -> str:
     delim = ":" if is_match else "-"
-    if show_line_numbers:
-        prefix = _colorize(str(line_no), COLOR_LINE_NO, use_color)
-        sep = "\t" if heading else ""
-        return f"{prefix}{delim}{sep}{text}"
-    return text
+    if not show_line_numbers:
+        return text
+    prefix = _colorize(str(line_no), COLOR_LINE_NO, use_color)
+    sep = "\t" if heading else ""
+    return f"{prefix}{delim}{sep}{text}"
 
 
 def _merge_ranges(ranges: list[tuple[int, int]]) -> list[tuple[int, int]]:

{rlmgrep-0.1.4 → rlmgrep-0.1.5}/rlmgrep.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rlmgrep
-Version: 0.1.4
+Version: 0.1.5
 Summary: Grep-shaped CLI search powered by DSPy RLM
 Author: rlmgrep
 License: MIT
@@ -62,8 +62,6 @@ rlmgrep [options] "query" [paths...]
 Common options:
 
 - `-n` show line numbers (default)
-- `--no-line-number` hide line numbers
-- `-H` always show filenames (default)
 - `-C N` context lines before/after (grep-style)
 - `-A N` context lines after
 - `-B N` context lines before
@@ -120,7 +118,7 @@ rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
   - `1` = no matches
   - `2` = usage/config/error
 
-Agent tip: use `-n -H` and no context for parse-friendly output, then key off exit codes.
+Agent tip: use `-n` and no context for parse-friendly output, then key off exit codes.
 
 ## Regex-style queries (best effort)
 
@@ -160,7 +158,7 @@ file_hard_max = 1000
 # markitdown_image_llm_api_base = ""
 # markitdown_image_llm_prompt = ""
 # markitdown_enable_audio = false
-# markitdown_audio_model = "gpt-4o-mini-transcribe"
+# markitdown_audio_model = "gpt-4o-mini-transcribe-2025-12-15"
 # markitdown_audio_provider = "openai"
 # markitdown_audio_api_key = ""
 # markitdown_audio_api_base = ""
@@ -180,7 +178,7 @@ If more than one provider key is set and the model does not make the provider ob
 ## Non-text files (PDF, images, audio)
 
 - PDF files are parsed with `pypdf`. Each page gets a marker line `===== Page N =====`, and output lines include a `page=N` suffix.
-- Images and audio are converted via `markitdown` when enabled in config. For image/audio conversion, an `openai` Python client is required.
+- Images and audio are converted via `markitdown` when enabled in config. Image conversion supports `openai`, `anthropic`, and `gemini` providers; audio conversion currently supports `openai` only.
 - Converted image/audio text is cached in sidecar files named `<original>.<ext>.md` next to the original file and reused on subsequent runs.
 - Use `-a/--text` to force binary files to be read as text (UTF-8 with replacement).
 
@@ -188,7 +186,7 @@ If more than one provider key is set and the model does not make the provider ob
 
 - Prefer narrow corpora (globs/types) to reduce token usage.
 - Use `--max-llm-calls` to cap costs; combine with small `--max-iterations` for safety.
-- For reproducible parsing, use `-n -H` and avoid context (`-C/-A/-B`).
+- For reproducible parsing, use `-n` and avoid context (`-C/-A/-B`).
   
 ## Development