rlmgrep 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

rlmgrep/__init__.py

@@ -1,2 +1,2 @@
 __all__ = ["__version__"]
-__version__ = "0.1.6"
+__version__ = "0.1.8"

{rlmgrep-0.1.6.dist-info → rlmgrep-0.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rlmgrep
-Version: 0.1.6
+Version: 0.1.8
 Summary: Grep-shaped CLI search powered by DSPy RLM
 Author: rlmgrep
 License: MIT
@@ -17,9 +17,9 @@ Grep-shaped search powered by DSPy RLM. It accepts a natural-language query, sca
 ## Quickstart
 
 ```sh
-uv tool install --python 3.11 rlmgrep
+uv tool install rlmgrep
 # or from GitHub:
-# uv tool install --python 3.11 git+https://github.com/halfprice06/rlmgrep.git
+# uv tool install git+https://github.com/halfprice06/rlmgrep.git
 
 export OPENAI_API_KEY=...  # or set keys in ~/.rlmgrep
 rlmgrep "where are API keys read" rlmgrep/
@@ -31,6 +31,20 @@ rlmgrep "where are API keys read" rlmgrep/
 - Deno runtime (DSPy RLM uses a Deno-based interpreter)
 - API key for your chosen provider (OpenAI, Anthropic, Gemini, etc.)
 
+## Non-text Files (PDF + Office + Media)
+
+One of rlmgrep’s most useful features is that it can “grep” **PDFs and Office files** by converting them into text before the RLM search runs.
+
+How it works:
+- **PDFs** are parsed with `pypdf`. Each page gets a marker line like `===== Page N =====`, and output lines include a `page=N` suffix. Line numbers refer to the extracted text (not PDF coordinates).
+- **Office & binary docs** (`.docx`, `.pptx`, `.xlsx`, `.html`, `.zip`, etc.) are converted to Markdown via **MarkItDown**. This happens during ingestion, so rlmgrep can search them like any other text file.
+- **Images** can be described by a vision model through MarkItDown (OpenAI/Anthropic/Gemini).
+- **Audio** transcription is supported through OpenAI when enabled.
+
+Sidecar caching:
+- For images/audio, converted text is cached next to the original file as `<original>.<ext>.md` and reused on later runs.
+- Use `-a/--text` if you want to treat binary files as raw text (UTF‑8 with replacement) and skip conversion.
+
 ## Install Deno
 
 DSPy requires the Deno runtime. Install it with the official scripts:
@@ -70,7 +84,8 @@ Common options:
 - `--no-recursive` do not recurse directories
 - `-a`, `--text` treat binary files as text
 - `-y`, `--yes` skip file count confirmation
-- `--stdin-files` treat stdin as newline-delimited file paths
+- `--files-from-stdin` treat stdin as newline-delimited file paths (e.g., `rg -l`)
+- `--files-from-rg` alias for `--files-from-stdin`
 - `--model`, `--sub-model` override model names
 - `--api-key`, `--api-base`, `--model-type` override provider settings
 - `--max-iterations`, `--max-llm-calls` cap RLM search effort
@@ -173,12 +188,13 @@ CLI flags override config values. Model keys are resolved as:
 
 If more than one provider key is set and the model does not make the provider obvious, rlmgrep emits a warning and requires an explicit `--api-key`.
 
-## Non-text files (PDF, images, audio)
+## Skill (Anthropic-style)
+
+A ready-to-copy skill lives in:
+
+- `skills/rlmgrep-usage/SKILL.md`
 
-- 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. 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).
+Install it by copying the folder into your agent’s skills directory (for example, `~/.claude/skills/rlmgrep-usage/`), then invoke it as `$rlmgrep-usage` in prompts. This is a lightweight, documentation-only skill meant to guide when to use rlmgrep vs `rg`/`grep`.
 
 ## Development
 

{rlmgrep-0.1.6.dist-info → rlmgrep-0.1.8.dist-info}/RECORD

@@ -1,4 +1,4 @@
-rlmgrep/__init__.py,sha256=uEY-o5UpO0zjCdZ1SCWaClP-xXaDZDIXmwIfxAtFffI,48
+rlmgrep/__init__.py,sha256=J-ZAXY7tnYw7E5X3eod4-Q1hZ1FtnW7JHRKkkRpff-c,48
 rlmgrep/__main__.py,sha256=MHKZ_ae3fSLGTLUUMOx15fWdeOnJSHhq-zslRP5F5Lc,79
 rlmgrep/cli.py,sha256=eUdM9aC0znZFzjqj-4YmT0_ymisSc_lUwDVjRi4ZU-s,20589
 rlmgrep/config.py,sha256=u1iz-nI8dj-dZETbpIki3RQefHJEyi5oE5zE4_IR8kg,2399
@@ -7,8 +7,8 @@ rlmgrep/ingest.py,sha256=uCz2el9B-RIT9umFo-gFEdAsmWPP1IJOArFFQY0D_1A,9127
 rlmgrep/interpreter.py,sha256=s_nMRxLlAU9C0JmUzUBW5NbVbuH67doVWF54K54STlA,2478
 rlmgrep/render.py,sha256=OYZy7BuJJe-KsDhEGAz6JA5RGd65ZInPWf9wLDJE0ag,3554
 rlmgrep/rlm.py,sha256=i3rCTp8OABByF60Un5gO7265gaW4spwU0OFKIz4surg,5750
-rlmgrep-0.1.6.dist-info/METADATA,sha256=g9zfDLY_x-QCcMzB0pcyXWZ6FoXr_c67mLiVRrOcHyI,6318
-rlmgrep-0.1.6.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-rlmgrep-0.1.6.dist-info/entry_points.txt,sha256=UV6QkEbkwBO1JJ53mm84_n35tVyOczPvOQ14ga7vrCI,45
-rlmgrep-0.1.6.dist-info/top_level.txt,sha256=gTujSRsO58c80eN7aRH2cfe51FHxx8LJ1w1Y2YlHti0,8
-rlmgrep-0.1.6.dist-info/RECORD,,
+rlmgrep-0.1.8.dist-info/METADATA,sha256=C_gnUrUZ_Wktda5-QgX4qn0f1fZWqLUHwN6uSNGK5DQ,7157
+rlmgrep-0.1.8.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+rlmgrep-0.1.8.dist-info/entry_points.txt,sha256=UV6QkEbkwBO1JJ53mm84_n35tVyOczPvOQ14ga7vrCI,45
+rlmgrep-0.1.8.dist-info/top_level.txt,sha256=gTujSRsO58c80eN7aRH2cfe51FHxx8LJ1w1Y2YlHti0,8
+rlmgrep-0.1.8.dist-info/RECORD,,