vimlm 0.0.3__tar.gz → 0.0.5__tar.gz

vimlm-0.0.5/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.2
+Name: vimlm
+Version: 0.0.5
+Summary: VimLM - LLM-powered Vim assistant
+Home-page: https://github.com/JosefAlbers/vimlm
+Author: Josef Albers
+Author-email: albersj66@gmail.com
+Requires-Python: >=3.12.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: nanollama==0.0.5b0
+Requires-Dist: mlx_lm_utils==0.0.1a0
+Requires-Dist: watchfiles==1.0.4
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# VimLM - Local LLM-Powered Coding Assistant for Vim
+
+![vimlm](https://github.com/user-attachments/assets/67a97048-48df-40c1-9109-53c759e85d96)
+
+An LLM-powered coding companion for Vim, inspired by GitHub Copilot/Cursor. Integrates contextual code understanding, summarization, and AI assistance directly into your Vim workflow.
+
+## Features
+
+- **Model Agnostic** - Use any MLX-compatible model via config file
+- **Vim-Native UX** - Ctrl-l/Ctrl-r keybindings and split-window responses
+- **Deep Context** - Understands code context from:
+    - Current file
+    - Visual selections
+    - Referenced files (`!@#$` syntax)
+    - Project directory structure
+- **Conversational Coding** - Iterative refinement with follow-up queries
+- **Air-Gapped Security** - 100% offline - no APIs, no tracking, no data leaks
+
+## Requirements
+
+- Apple M-series chip (M1/M2/M3/M4)
+- Python 3.12.8
+
+## Installation
+
+```zsh
+pip install vimlm
+```
+
+## Quick Start
+
+1. Launch with default model (DeepSeek-R1-Distill-Qwen-7B-4bit):
+
+```zsh
+vimlm your_file.js
+```
+
+2. **From Normal Mode**:
+    - `Ctrl-l`: Send current line + file context
+    - Example prompt: "Regex for removing html tags in item.content"
+
+3. **From Visual Mode**:
+    - Select code → `Ctrl-l`: Send selection + file context
+    - Example prompt: "Convert this to async/await syntax"
+
+4. **Add Context**: Use `!@#$` to include additional files/folders:
+    - `!@#$` (no path): Current folder
+    - `!@#$ ~/scrap/jph00/hypermedia-applications.summ.md`: Specific folder
+    - `!@#$ ~/wtm/utils.py`: Specific file
+    - Example prompt: "AJAX-ify this app !@#$ ~/scrap/jph00/hypermedia-applications.summ.md"
+
+5. **Follow-Up**: After initial response:
+    - `Ctrl-r`: Continue thread
+    - Example follow-up: "In Manifest V3"
+
+## Advanced Configuration
+
+### Custom Model Setup
+
+1. **Browse models**: [MLX Community Models on Hugging Face](https://huggingface.co/mlx-community)
+
+2. **Edit config file**:
+
+```json
+{
+ "LLM_MODEL": "/path/to/your/mlx_model"
+}
+```
+
+3. **Save to**:
+
+```
+~/vimlm/cfg.json
+```
+
+4. **Restart VimLM**
+
+## Key Bindings
+
+| Binding    | Mode          | Action                                 |
+|------------|---------------|----------------------------------------|
+| `Ctrl-l`   | Normal/Visual | Send current file + selection to LLM   |
+| `Ctrl-r`   | Normal        | Continue conversation                  |
+| `Esc`      | Prompt        | Cancel input                           |
+
+

vimlm-0.0.5/README.md

@@ -0,0 +1,86 @@
+# VimLM - Local LLM-Powered Coding Assistant for Vim
+
+![vimlm](https://github.com/user-attachments/assets/67a97048-48df-40c1-9109-53c759e85d96)
+
+An LLM-powered coding companion for Vim, inspired by GitHub Copilot/Cursor. Integrates contextual code understanding, summarization, and AI assistance directly into your Vim workflow.
+
+## Features
+
+- **Model Agnostic** - Use any MLX-compatible model via config file
+- **Vim-Native UX** - Ctrl-l/Ctrl-r keybindings and split-window responses
+- **Deep Context** - Understands code context from:
+    - Current file
+    - Visual selections
+    - Referenced files (`!@#$` syntax)
+    - Project directory structure
+- **Conversational Coding** - Iterative refinement with follow-up queries
+- **Air-Gapped Security** - 100% offline - no APIs, no tracking, no data leaks
+
+## Requirements
+
+- Apple M-series chip (M1/M2/M3/M4)
+- Python 3.12.8
+
+## Installation
+
+```zsh
+pip install vimlm
+```
+
+## Quick Start
+
+1. Launch with default model (DeepSeek-R1-Distill-Qwen-7B-4bit):
+
+```zsh
+vimlm your_file.js
+```
+
+2. **From Normal Mode**:
+    - `Ctrl-l`: Send current line + file context
+    - Example prompt: "Regex for removing html tags in item.content"
+
+3. **From Visual Mode**:
+    - Select code → `Ctrl-l`: Send selection + file context
+    - Example prompt: "Convert this to async/await syntax"
+
+4. **Add Context**: Use `!@#$` to include additional files/folders:
+    - `!@#$` (no path): Current folder
+    - `!@#$ ~/scrap/jph00/hypermedia-applications.summ.md`: Specific folder
+    - `!@#$ ~/wtm/utils.py`: Specific file
+    - Example prompt: "AJAX-ify this app !@#$ ~/scrap/jph00/hypermedia-applications.summ.md"
+
+5. **Follow-Up**: After initial response:
+    - `Ctrl-r`: Continue thread
+    - Example follow-up: "In Manifest V3"
+
+## Advanced Configuration
+
+### Custom Model Setup
+
+1. **Browse models**: [MLX Community Models on Hugging Face](https://huggingface.co/mlx-community)
+
+2. **Edit config file**:
+
+```json
+{
+ "LLM_MODEL": "/path/to/your/mlx_model"
+}
+```
+
+3. **Save to**:
+
+```
+~/vimlm/cfg.json
+```
+
+4. **Restart VimLM**
+
+## Key Bindings
+
+| Binding    | Mode          | Action                                 |
+|------------|---------------|----------------------------------------|
+| `Ctrl-l`   | Normal/Visual | Send current file + selection to LLM   |
+| `Ctrl-r`   | Normal        | Continue conversation                  |
+| `Esc`      | Prompt        | Cancel input                           |
+
+

{vimlm-0.0.3 → vimlm-0.0.5}/setup.py

@@ -5,7 +5,7 @@ with open("requirements.txt") as f:
 
 setup(
     name="vimlm",
-    version="0.0.3",
+    version="0.0.5",
     author="Josef Albers",
     author_email="albersj66@gmail.com",
     readme='README.md',
@@ -15,7 +15,7 @@ setup(
     url="https://github.com/JosefAlbers/vimlm",
     # packages=find_packages(),
     py_modules=['vimlm'],
-    python_requires=">=3.13.1",
+    python_requires=">=3.12.8",
     install_requires=requirements,
     entry_points={
         "console_scripts": [

vimlm-0.0.5/vimlm.egg-info/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.2
+Name: vimlm
+Version: 0.0.5
+Summary: VimLM - LLM-powered Vim assistant
+Home-page: https://github.com/JosefAlbers/vimlm
+Author: Josef Albers
+Author-email: albersj66@gmail.com
+Requires-Python: >=3.12.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: nanollama==0.0.5b0
+Requires-Dist: mlx_lm_utils==0.0.1a0
+Requires-Dist: watchfiles==1.0.4
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# VimLM - Local LLM-Powered Coding Assistant for Vim
+
+![vimlm](https://github.com/user-attachments/assets/67a97048-48df-40c1-9109-53c759e85d96)
+
+An LLM-powered coding companion for Vim, inspired by GitHub Copilot/Cursor. Integrates contextual code understanding, summarization, and AI assistance directly into your Vim workflow.
+
+## Features
+
+- **Model Agnostic** - Use any MLX-compatible model via config file
+- **Vim-Native UX** - Ctrl-l/Ctrl-r keybindings and split-window responses
+- **Deep Context** - Understands code context from:
+    - Current file
+    - Visual selections
+    - Referenced files (`!@#$` syntax)
+    - Project directory structure
+- **Conversational Coding** - Iterative refinement with follow-up queries
+- **Air-Gapped Security** - 100% offline - no APIs, no tracking, no data leaks
+
+## Requirements
+
+- Apple M-series chip (M1/M2/M3/M4)
+- Python 3.12.8
+
+## Installation
+
+```zsh
+pip install vimlm
+```
+
+## Quick Start
+
+1. Launch with default model (DeepSeek-R1-Distill-Qwen-7B-4bit):
+
+```zsh
+vimlm your_file.js
+```
+
+2. **From Normal Mode**:
+    - `Ctrl-l`: Send current line + file context
+    - Example prompt: "Regex for removing html tags in item.content"
+
+3. **From Visual Mode**:
+    - Select code → `Ctrl-l`: Send selection + file context
+    - Example prompt: "Convert this to async/await syntax"
+
+4. **Add Context**: Use `!@#$` to include additional files/folders:
+    - `!@#$` (no path): Current folder
+    - `!@#$ ~/scrap/jph00/hypermedia-applications.summ.md`: Specific folder
+    - `!@#$ ~/wtm/utils.py`: Specific file
+    - Example prompt: "AJAX-ify this app !@#$ ~/scrap/jph00/hypermedia-applications.summ.md"
+
+5. **Follow-Up**: After initial response:
+    - `Ctrl-r`: Continue thread
+    - Example follow-up: "In Manifest V3"
+
+## Advanced Configuration
+
+### Custom Model Setup
+
+1. **Browse models**: [MLX Community Models on Hugging Face](https://huggingface.co/mlx-community)
+
+2. **Edit config file**:
+
+```json
+{
+ "LLM_MODEL": "/path/to/your/mlx_model"
+}
+```
+
+3. **Save to**:
+
+```
+~/vimlm/cfg.json
+```
+
+4. **Restart VimLM**
+
+## Key Bindings
+
+| Binding    | Mode          | Action                                 |
+|------------|---------------|----------------------------------------|
+| `Ctrl-l`   | Normal/Visual | Send current file + selection to LLM   |
+| `Ctrl-r`   | Normal        | Continue conversation                  |
+| `Esc`      | Prompt        | Cancel input                           |
+
+

vimlm-0.0.5/vimlm.egg-info/requires.txt

@@ -0,0 +1,3 @@
+nanollama==0.0.5b0
+mlx_lm_utils==0.0.1a0
+watchfiles==1.0.4

{vimlm-0.0.3 → vimlm-0.0.5}/vimlm.py

@@ -17,7 +17,6 @@ import subprocess
 import json
 import os
 from watchfiles import awatch
-from nanollama32 import Chat
 import shutil
 import time
 from itertools import accumulate
@@ -26,23 +25,22 @@ import tempfile
 from pathlib import Path
 from string import Template
 
-DEBUG = False 
+DEBUG = True
+LLM_MODEL = "mlx-community/DeepSeek-R1-Distill-Qwen-7B-4bit"
 NUM_TOKEN = 2000
 SEP_CMD = '!@#$'
-CACHE_DIR = os.path.expanduser("~/vimlm")
+VIMLM_DIR = os.path.expanduser("~/vimlm")
 WATCH_DIR = os.path.expanduser("~/vimlm/watch_dir")
+CFG_FILE = "cfg.json"
 LOG_FILE = "log.json"
-CACHE_FILE = "cache.json"
+LTM_FILE = "cache.json"
 OUT_FILE = "response.md"
-FILES = ["context", "yank", "user", "tree"]  
-LOG_PATH = os.path.join(CACHE_DIR, LOG_FILE)
-CACHE_PATH = os.path.join(CACHE_DIR, CACHE_FILE)
+IN_FILES = ["context", "yank", "user", "tree"]
+CFG_PATH = os.path.join(VIMLM_DIR, CFG_FILE)
+LOG_PATH = os.path.join(VIMLM_DIR, LOG_FILE)
+LTM_PATH = os.path.join(VIMLM_DIR, LTM_FILE)
 OUT_PATH = os.path.join(WATCH_DIR, OUT_FILE) 
 
-if os.path.exists(WATCH_DIR):
-    shutil.rmtree(WATCH_DIR)
-os.makedirs(WATCH_DIR)
-
 def toout(s, key='tovim'):
     with open(OUT_PATH, 'w', encoding='utf-8') as f:
         f.write(s)
@@ -51,18 +49,40 @@ def toout(s, key='tovim'):
 def tolog(log, key='debug'):
     if not DEBUG and key == 'debug':
         return
-    if os.path.exists(LOG_PATH):
+    try:
         with open(LOG_PATH, "r", encoding="utf-8") as log_f:
             logs = json.load(log_f)
-    else:
+    except:
         logs = []
     logs.append(dict(key=key, log=log, timestamp=time.ctime()))
     with open(LOG_PATH, "w", encoding="utf-8") as log_f:
         json.dump(logs, log_f, indent=2)
 
+if os.path.exists(WATCH_DIR):
+    shutil.rmtree(WATCH_DIR)
+os.makedirs(WATCH_DIR)
+
+try:
+    with open(CFG_PATH, "r") as f:
+        config = json.load(f)
+    DEBUG = config.get("DEBUG", DEBUG)
+    LLM_MODEL = config.get("LLM_MODEL", LLM_MODEL)
+    NUM_TOKEN = config.get("NUM_TOKEN", NUM_TOKEN)
+    SEP_CMD = config.get("SEP_CMD", SEP_CMD)
+except Exception as e:
+    tolog(str(e))
+    with open(CFG_PATH, 'w') as f:
+        json.dump(dict(DEBUG=DEBUG, LLM_MODEL=LLM_MODEL, NUM_TOKEN=NUM_TOKEN, SEP_CMD=SEP_CMD), f, indent=2)
+
 toout('Loading LLM...')
-chat = Chat(variant='uncn_llama_32_3b_it')
-toout('LLM is ready')
+if LLM_MODEL is None:
+    from nanollama32 import Chat
+    chat = Chat(variant='uncn_llama_32_3b_it')
+    toout('LLM is ready')
+else:
+    from mlx_lm_utils import Chat
+    chat = Chat(model_path=LLM_MODEL)
+    toout(f'{LLM_MODEL.split('/')[-1]} is ready')
 
 def is_binary(file_path):
     try:
@@ -102,11 +122,11 @@ def split_str(doc, max_len=2000, get_len=len):
             chunks.append("".join(current_chunk))
     return chunks
 
-def get_context(src_path, max_len=2000, get_len=len):
+def retrieve(src_path, max_len=2000, get_len=len):
     src_path = os.path.expanduser(src_path)
     result = {}
     if not os.path.exists(src_path):
-        tolog(f"The path {src_path} does not exist.", 'get_context')
+        tolog(f"The path {src_path} does not exist.", 'retrieve')
         return result
     if os.path.isfile(src_path):
         try:
@@ -114,7 +134,7 @@ def get_context(src_path, max_len=2000, get_len=len):
                 content = f.read()
             result = {src_path:dict(timestamp=os.path.getmtime(src_path), list_str=split_str(content, max_len=max_len, get_len=get_len))}
         except Exception as e:
-            tolog(f'Skipped {filename} due to {e}', 'get_context')
+            tolog(f'Skipped {filename} due to {e}', 'retrieve')
         return result
     for filename in os.listdir(src_path):
         try:
@@ -126,20 +146,17 @@ def get_context(src_path, max_len=2000, get_len=len):
                     content = f.read()
                 result[file_path] = dict(timestamp=os.path.getmtime(file_path), list_str=split_str(content, max_len=max_len, get_len=get_len))
         except Exception as e:
-            tolog(f'Skipped {filename} due to {e}', 'get_context')
+            tolog(f'Skipped {filename} due to {e}', 'retrieve')
             continue
     return result
 
-def get_ntok(s):
-    return len(chat.tokenizer.encode(s)[0])
-
 def ingest(src):
-    def load_cache(cache_path=CACHE_PATH):
+    def load_cache(cache_path=LTM_PATH):
         if os.path.exists(cache_path):
             with open(cache_path, 'r', encoding='utf-8') as f:
                 return json.load(f)
         return {}
-    def dump_cache(new_data, cache_path=CACHE_PATH):
+    def dump_cache(new_data, cache_path=LTM_PATH):
         current_data = load_cache(cache_path)
         for k, v in new_data.items():
             if k not in current_data or v['timestamp'] > current_data[k]['timestamp']:
@@ -149,7 +166,7 @@ def ingest(src):
     toout('Ingesting...')
     format_ingest = '{volat}{incoming}\n\n---\n\nPlease provide a succint bullet point summary for above:'
     format_volat = 'Here is a summary of part 1 of **{k}**:\n\n---\n\n{newsum}\n\n---\n\nHere is the next part:\n\n---\n\n'
-    dict_doc = get_context(src, get_len=get_ntok)
+    dict_doc = retrieve(src, get_len=chat.get_ntok)
     dict_sum = {}
     cache = load_cache()
     for k, v in dict_doc.items():
@@ -166,14 +183,14 @@ def ingest(src):
             accum = ''
             for s in list_str:
                 chat.reset()
-                newsum = chat(format_ingest.format(volat=volat, incoming=s.strip()), max_new=max_new_sum, verbose=False, stream=None)[0][:-10].strip()
+                newsum = chat(format_ingest.format(volat=volat, incoming=s.strip()), max_new=max_new_sum, verbose=False, stream=None)['text']
                 accum += newsum + ' ...\n'
                 volat = format_volat.format(k=k, newsum=newsum)
         else:
             accum = list_str[0]
         chat.reset()
         toout('')
-        chat_summary = chat(format_ingest.format(volat=f'**{k}**:\n', incoming=accum), max_new=int(NUM_TOKEN/4), verbose=False, stream=OUT_PATH)[0][:-10].strip()
+        chat_summary = chat(format_ingest.format(volat=f'**{k}**:\n', incoming=accum), max_new=int(NUM_TOKEN/4), verbose=False, stream=OUT_PATH)['text']
         dict_sum[k] = dict(timestamp=v_stamp, summary=chat_summary)
     dump_cache(dict_sum)
     result = ''
@@ -197,10 +214,10 @@ async def monitor_directory():
     async for changes in awatch(WATCH_DIR):
         found_files = {os.path.basename(f) for _, f in changes}
         tolog(f'{found_files=}') # DEBUG
-        if FILES[-1] in found_files and set(FILES).issubset(set(os.listdir(WATCH_DIR))):
+        if IN_FILES[-1] in found_files and set(IN_FILES).issubset(set(os.listdir(WATCH_DIR))):
             tolog(f'listdir()={os.listdir(WATCH_DIR)}') # DEBUG
             data = {}
-            for file in FILES:
+            for file in IN_FILES:
                 path = os.path.join(WATCH_DIR, file)
                 with open(path, 'r', encoding='utf-8') as f:
                     data[file] = f.read().strip()
@@ -241,8 +258,9 @@ async def process_files(data):
     prompt = str_template.format(**data)
     tolog(prompt, 'tollm')
     toout('')
-    response = chat(prompt, max_new=NUM_TOKEN - get_ntok(prompt), verbose=False, stream=OUT_PATH)[0][:-10].strip()
-    toout(response)
+    response = chat(prompt, max_new=NUM_TOKEN - chat.get_ntok(prompt), verbose=False, stream=OUT_PATH)
+    toout(response['text'])
+    tolog(response['benchmark'])
 
 VIMLMSCRIPT = Template(r"""
 let s:watched_dir = expand('$WATCH_DIR')

vimlm-0.0.3/PKG-INFO

@@ -1,84 +0,0 @@
-Metadata-Version: 2.2
-Name: vimlm
-Version: 0.0.3
-Summary: VimLM - LLM-powered Vim assistant
-Home-page: https://github.com/JosefAlbers/vimlm
-Author: Josef Albers
-Author-email: albersj66@gmail.com
-Requires-Python: >=3.13.1
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: nanollama==0.0.3
-Requires-Dist: watchfiles==1.0.4
-Dynamic: author
-Dynamic: author-email
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# VimLM - Vim Language Model Assistant for privacy-conscious developers
-
-![vimlm](https://github.com/user-attachments/assets/4aa39efe-aa6d-4363-8fe1-cf964d7f849c)
-
-VimLM brings AI-powered assistance directly into Vim, keeping your workflow smooth and uninterrupted. Instead of constantly switching between your editor and external tools, VimLM provides real-time, context-aware suggestions, explanations, and code insights—all within Vim.
-
-Unlike proprietary cloud-based AI models, VimLM runs entirely offline, ensuring complete privacy, data security, and control. You’re not just using a tool—you own it. Fine-tune, modify, or extend it as needed, without reliance on big tech platforms.
-
-## Features
-
-- **Real-Time Interaction with local LLMs**: Runs **fully offline** with local models (default: uncensored Llama-3.2-3B).
-- **Integration with Vim's Native Workflow**: Simple Vim keybindings for quick access and split-window interface for non-intrusive responses.
-- **Context-Awareness Beyond Single Files**: Inline support for external documents and project files for richer, more informed responses.
-- **Conversational AI Assistance**: Goes beyond simple code suggestions-explains reasoning, provides alternative solutions, and allows interactive follow-ups. 
-- **Versatile Use Cases**: Not just for coding-use it for documentation lookup, general Q&A, or even casual (uncensored) conversations.
-
-## Installation
-
-```zsh
-pip install vimlm
-```
-
-## Usage
-
-1. Start Vim with VimLM:
-
-```zsh
-vimlm
-```
-
-or
-
-```zsh
-vimlm your_file.js
-```
-
-2. **From Normal Mode**:
-    - `Ctrl-l`: Send current line + file context
-    - Example prompt: "Regex for removing html tags in item.content"
-
-3. **From Visual Mode**:
-    - Select text → `Ctrl-l`: Send selection + file context
-    - Example prompt: "Convert this to async/await syntax"
-
-4. **Add Context**: Use `!@#$` to include additional files/folders:
-    - `!@#$` (no path): Current folder
-    - `!@#$ ~/scrap/jph00/hypermedia-applications.summ.md`: Specific folder
-    - `!@#$ ~/wtm/utils.py`: Specific file
-    - Example prompt: "AJAX-ify this app !@#$ ~/scrap/jph00/hypermedia-applications.summ.md"
-
-5. **Follow-Up**: After initial response:
-    - `Ctrl-R`: Continue thread
-    - Example follow-up: "In Manifest V3"
-
-## Key Bindings
-
-| Binding    | Mode          | Action                                 |
-|------------|---------------|----------------------------------------|
-| `Ctrl-L`   | Normal/Visual | Send current file + selection to LLM   |
-| `Ctrl-R`   | Normal        | Continue conversation                  |
-| `Esc`      | Prompt        | Cancel input                           |
-
-

vimlm-0.0.3/README.md

@@ -1,63 +0,0 @@
-# VimLM - Vim Language Model Assistant for privacy-conscious developers
-
-![vimlm](https://github.com/user-attachments/assets/4aa39efe-aa6d-4363-8fe1-cf964d7f849c)
-
-VimLM brings AI-powered assistance directly into Vim, keeping your workflow smooth and uninterrupted. Instead of constantly switching between your editor and external tools, VimLM provides real-time, context-aware suggestions, explanations, and code insights—all within Vim.
-
-Unlike proprietary cloud-based AI models, VimLM runs entirely offline, ensuring complete privacy, data security, and control. You’re not just using a tool—you own it. Fine-tune, modify, or extend it as needed, without reliance on big tech platforms.
-
-## Features
-
-- **Real-Time Interaction with local LLMs**: Runs **fully offline** with local models (default: uncensored Llama-3.2-3B).
-- **Integration with Vim's Native Workflow**: Simple Vim keybindings for quick access and split-window interface for non-intrusive responses.
-- **Context-Awareness Beyond Single Files**: Inline support for external documents and project files for richer, more informed responses.
-- **Conversational AI Assistance**: Goes beyond simple code suggestions-explains reasoning, provides alternative solutions, and allows interactive follow-ups. 
-- **Versatile Use Cases**: Not just for coding-use it for documentation lookup, general Q&A, or even casual (uncensored) conversations.
-
-## Installation
-
-```zsh
-pip install vimlm
-```
-
-## Usage
-
-1. Start Vim with VimLM:
-
-```zsh
-vimlm
-```
-
-or
-
-```zsh
-vimlm your_file.js
-```
-
-2. **From Normal Mode**:
-    - `Ctrl-l`: Send current line + file context
-    - Example prompt: "Regex for removing html tags in item.content"
-
-3. **From Visual Mode**:
-    - Select text → `Ctrl-l`: Send selection + file context
-    - Example prompt: "Convert this to async/await syntax"
-
-4. **Add Context**: Use `!@#$` to include additional files/folders:
-    - `!@#$` (no path): Current folder
-    - `!@#$ ~/scrap/jph00/hypermedia-applications.summ.md`: Specific folder
-    - `!@#$ ~/wtm/utils.py`: Specific file
-    - Example prompt: "AJAX-ify this app !@#$ ~/scrap/jph00/hypermedia-applications.summ.md"
-
-5. **Follow-Up**: After initial response:
-    - `Ctrl-R`: Continue thread
-    - Example follow-up: "In Manifest V3"
-
-## Key Bindings
-
-| Binding    | Mode          | Action                                 |
-|------------|---------------|----------------------------------------|
-| `Ctrl-L`   | Normal/Visual | Send current file + selection to LLM   |
-| `Ctrl-R`   | Normal        | Continue conversation                  |
-| `Esc`      | Prompt        | Cancel input                           |
-
-

vimlm-0.0.3/vimlm.egg-info/PKG-INFO

@@ -1,84 +0,0 @@
-Metadata-Version: 2.2
-Name: vimlm
-Version: 0.0.3
-Summary: VimLM - LLM-powered Vim assistant
-Home-page: https://github.com/JosefAlbers/vimlm
-Author: Josef Albers
-Author-email: albersj66@gmail.com
-Requires-Python: >=3.13.1
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: nanollama==0.0.3
-Requires-Dist: watchfiles==1.0.4
-Dynamic: author
-Dynamic: author-email
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# VimLM - Vim Language Model Assistant for privacy-conscious developers
-
-![vimlm](https://github.com/user-attachments/assets/4aa39efe-aa6d-4363-8fe1-cf964d7f849c)
-
-VimLM brings AI-powered assistance directly into Vim, keeping your workflow smooth and uninterrupted. Instead of constantly switching between your editor and external tools, VimLM provides real-time, context-aware suggestions, explanations, and code insights—all within Vim.
-
-Unlike proprietary cloud-based AI models, VimLM runs entirely offline, ensuring complete privacy, data security, and control. You’re not just using a tool—you own it. Fine-tune, modify, or extend it as needed, without reliance on big tech platforms.
-
-## Features
-
-- **Real-Time Interaction with local LLMs**: Runs **fully offline** with local models (default: uncensored Llama-3.2-3B).
-- **Integration with Vim's Native Workflow**: Simple Vim keybindings for quick access and split-window interface for non-intrusive responses.
-- **Context-Awareness Beyond Single Files**: Inline support for external documents and project files for richer, more informed responses.
-- **Conversational AI Assistance**: Goes beyond simple code suggestions-explains reasoning, provides alternative solutions, and allows interactive follow-ups. 
-- **Versatile Use Cases**: Not just for coding-use it for documentation lookup, general Q&A, or even casual (uncensored) conversations.
-
-## Installation
-
-```zsh
-pip install vimlm
-```
-
-## Usage
-
-1. Start Vim with VimLM:
-
-```zsh
-vimlm
-```
-
-or
-
-```zsh
-vimlm your_file.js
-```
-
-2. **From Normal Mode**:
-    - `Ctrl-l`: Send current line + file context
-    - Example prompt: "Regex for removing html tags in item.content"
-
-3. **From Visual Mode**:
-    - Select text → `Ctrl-l`: Send selection + file context
-    - Example prompt: "Convert this to async/await syntax"
-
-4. **Add Context**: Use `!@#$` to include additional files/folders:
-    - `!@#$` (no path): Current folder
-    - `!@#$ ~/scrap/jph00/hypermedia-applications.summ.md`: Specific folder
-    - `!@#$ ~/wtm/utils.py`: Specific file
-    - Example prompt: "AJAX-ify this app !@#$ ~/scrap/jph00/hypermedia-applications.summ.md"
-
-5. **Follow-Up**: After initial response:
-    - `Ctrl-R`: Continue thread
-    - Example follow-up: "In Manifest V3"
-
-## Key Bindings
-
-| Binding    | Mode          | Action                                 |
-|------------|---------------|----------------------------------------|
-| `Ctrl-L`   | Normal/Visual | Send current file + selection to LLM   |
-| `Ctrl-R`   | Normal        | Continue conversation                  |
-| `Esc`      | Prompt        | Cancel input                           |
-
-

vimlm-0.0.3/vimlm.egg-info/requires.txt

@@ -1,2 +0,0 @@
-nanollama==0.0.3
-watchfiles==1.0.4