docpilot-cli 1.0.2__tar.gz → 1.0.3__tar.gz

{docpilot_cli-1.0.2 → docpilot_cli-1.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docpilot-cli
-Version: 1.0.2
+Version: 1.0.3
 Summary: A local-first RAG pipeline CLI tool
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -59,9 +59,11 @@ pip install "docpilot-cli[pdf]"
 ```
 
 ### Prerequisites
+
 1. **Python 3.12+**
 2. **[Ollama](https://ollama.com/)**: Installed and running in the background.
 3. Pull your preferred models:
+
 ```bash
 ollama pull qwen2.5:latest
 ollama pull mxbai-embed-large:335m
@@ -71,9 +73,10 @@ ollama pull mxbai-embed-large:335m
 
 ## 🛠️ Quick Start
 
-The very first time you run a DocPilot command, it will launch the **Interactive Setup Wizard** to help you configure your chat and embedding models. 
+The very first time you run a DocPilot command, it will launch the **Interactive Setup Wizard** to help you configure your chat and embedding models.
 
 ### 1. Ingest Knowledge
+
 Point DocPilot to any documentation site, sitemap, PDF, or CSV:
 
 ```bash
@@ -91,6 +94,7 @@ docpilot ingest "./data/faq.csv"
 > If you installed via standard `pip` and get a "command not found" error because your binary path isn't configured, you can always run docpilot by prefixing commands with `python -m docpilot` (e.g., `python -m docpilot ingest ...`).
 
 ### 2. Ask Questions
+
 Query your newly created local knowledge base:
 
 ```bash
@@ -104,26 +108,34 @@ docpilot ask "How do I create a virtual environment?"
 Manage your configuration, models, and local database with ease.
 
 ### `docpilot setup`
+
 Re-run the interactive setup wizard at any time to change your default models.
 
 ### `docpilot project`
+
 Switch to a different project or check the active project. Each project has its own isolated vector database.
+
 ```bash
 docpilot project
 docpilot project <project-name>
 ```
 
 ### `docpilot clear`
+
 Wipe your local Chroma vector database to start fresh. Prompts for safety confirmation.
 
 ### `docpilot speed [profile]`
+
 Adjust the retrieval and generation settings for your desired use case.
+
 - `fast`: Lower latency, shorter context limits.
 - `balanced`: Default trade-off.
 - `quality`: Larger context, more comprehensive answers, slower inference.
 
 ### `docpilot model`
+
 Manually manage your Ollama models without the interactive setup wizard.
+
 ```bash
 docpilot model list
 docpilot model set <chat-model>
@@ -131,9 +143,11 @@ docpilot model setembed <embedding-model>
 ```
 
 ### `docpilot render`
+
 Parse and beautifully render any markdown file or text string directly in your terminal.
 
 ### `docpilot show`
+
 Display your current project version and configuration in beautiful ASCII art.
 
 ---
@@ -156,6 +170,7 @@ DocPilot employs an optimized RAG (Retrieval-Augmented Generation) pipeline:
 Contributions are welcome! If you are using DocPilot for your daily workflows or in a hackathon, feel free to open issues and pull requests.
 
 To set up a local development environment:
+
 ```bash
 git clone https://github.com/yourusername/docpilot.git
 cd docpilot

{docpilot_cli-1.0.2 → docpilot_cli-1.0.3}/README.md

@@ -37,9 +37,11 @@ pip install "docpilot-cli[pdf]"
 ```
 
 ### Prerequisites
+
 1. **Python 3.12+**
 2. **[Ollama](https://ollama.com/)**: Installed and running in the background.
 3. Pull your preferred models:
+
 ```bash
 ollama pull qwen2.5:latest
 ollama pull mxbai-embed-large:335m
@@ -49,9 +51,10 @@ ollama pull mxbai-embed-large:335m
 
 ## 🛠️ Quick Start
 
-The very first time you run a DocPilot command, it will launch the **Interactive Setup Wizard** to help you configure your chat and embedding models. 
+The very first time you run a DocPilot command, it will launch the **Interactive Setup Wizard** to help you configure your chat and embedding models.
 
 ### 1. Ingest Knowledge
+
 Point DocPilot to any documentation site, sitemap, PDF, or CSV:
 
 ```bash
@@ -69,6 +72,7 @@ docpilot ingest "./data/faq.csv"
 > If you installed via standard `pip` and get a "command not found" error because your binary path isn't configured, you can always run docpilot by prefixing commands with `python -m docpilot` (e.g., `python -m docpilot ingest ...`).
 
 ### 2. Ask Questions
+
 Query your newly created local knowledge base:
 
 ```bash
@@ -82,26 +86,34 @@ docpilot ask "How do I create a virtual environment?"
 Manage your configuration, models, and local database with ease.
 
 ### `docpilot setup`
+
 Re-run the interactive setup wizard at any time to change your default models.
 
 ### `docpilot project`
+
 Switch to a different project or check the active project. Each project has its own isolated vector database.
+
 ```bash
 docpilot project
 docpilot project <project-name>
 ```
 
 ### `docpilot clear`
+
 Wipe your local Chroma vector database to start fresh. Prompts for safety confirmation.
 
 ### `docpilot speed [profile]`
+
 Adjust the retrieval and generation settings for your desired use case.
+
 - `fast`: Lower latency, shorter context limits.
 - `balanced`: Default trade-off.
 - `quality`: Larger context, more comprehensive answers, slower inference.
 
 ### `docpilot model`
+
 Manually manage your Ollama models without the interactive setup wizard.
+
 ```bash
 docpilot model list
 docpilot model set <chat-model>
@@ -109,9 +121,11 @@ docpilot model setembed <embedding-model>
 ```
 
 ### `docpilot render`
+
 Parse and beautifully render any markdown file or text string directly in your terminal.
 
 ### `docpilot show`
+
 Display your current project version and configuration in beautiful ASCII art.
 
 ---
@@ -134,6 +148,7 @@ DocPilot employs an optimized RAG (Retrieval-Augmented Generation) pipeline:
 Contributions are welcome! If you are using DocPilot for your daily workflows or in a hackathon, feel free to open issues and pull requests.
 
 To set up a local development environment:
+
 ```bash
 git clone https://github.com/yourusername/docpilot.git
 cd docpilot
@@ -145,4 +160,4 @@ uv run pytest
 
 ## 📄 License
 
-This project is licensed under the MIT License.
+This project is licensed under the MIT License.

{docpilot_cli-1.0.2 → docpilot_cli-1.0.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docpilot-cli"
-version = "1.0.2"
+version = "1.0.3"
 description = "A local-first RAG pipeline CLI tool"
 readme = "README.md"
 requires-python = ">=3.12"

{docpilot_cli-1.0.2 → docpilot_cli-1.0.3}/src/docpilot/chat.py

@@ -1,5 +1,6 @@
 from langchain_ollama.llms import OllamaLLM as Ollama
 from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
 import os
 from . import store
 from langchain_chroma import Chroma
@@ -18,16 +19,23 @@ model = Ollama(
     temperature=float(config.get("temperature", 0.1)),
 )
 
-
 def _get_vectorstore():
     """Get vectorstore for the active project."""
     embeddings = OllamaEmbeddings(model=config.get("default_embed_model", "mxbai-embed-large:335m"))
     db_location = store.get_active_project_path()
     return Chroma(collection_name="documents", persist_directory=str(db_location), embedding_function=embeddings)
 
-
 retriever = None
 
+# Query Transformation Chain 
+rewrite_template = """You are an AI assistant helping to formulate a search query for a vector database.
+Given the user's vague or short input, rewrite it into a precise search query or a set of keywords that will be used to retrieve relevant documents.
+Just output the query, do not add any explanation or conversational text.
+User input: {question}
+Search query:"""
+rewrite_prompt = ChatPromptTemplate.from_template(rewrite_template)
+rewrite_chain = rewrite_prompt | model | StrOutputParser()
+
 template = """
 You are an assistant for answering questions based on the following ingested documents. 
 Use the information in the documents to answer the question as best as you can. 
@@ -59,12 +67,17 @@ def _build_bounded_context(docs, max_total_chars: int = 6000, max_doc_chars: int
 def askai(question):
     vectorstore = _get_vectorstore()
     retriever = vectorstore.as_retriever(search_kwargs={"k": retrieval_k})
-    rag = retriever.invoke(question)
+    
+    # Rewrite the vague prompt into keywords/search query before hitting the vector DB
+    search_query = rewrite_chain.invoke({"question": question}).strip()
+    rag = retriever.invoke(search_query)
     rag_text = _build_bounded_context(
         rag,
         max_total_chars=max_context_chars,
         max_doc_chars=max_doc_chars,
     )
+    if rag_text == "":
+        print("NO RAG obtained add some documents to ingest")
     result = chain.invoke({"reviews": rag_text, "question": question})
     return result
 

{docpilot_cli-1.0.2 → docpilot_cli-1.0.3}/src/docpilot/cli.py

@@ -20,11 +20,18 @@ console = Console()
 
 app = typer.Typer()
 
-# Project metadata
-PROJECT_VERSION = "1.0.2"
-PROJECT_NAME = "docpilot"
-PROJECT_DESCRIPTION = "A local-first RAG pipeline CLI tool"
+from importlib.metadata import version, metadata, PackageNotFoundError
 
+# Project metadata
+try:
+    PROJECT_VERSION = version("docpilot-cli")
+    meta = metadata("docpilot-cli")
+    PROJECT_NAME = meta.get("Name", "docpilot")
+    PROJECT_DESCRIPTION = meta.get("Summary", "A local-first RAG pipeline CLI tool")
+except PackageNotFoundError:
+    PROJECT_VERSION = "unknown"
+    PROJECT_NAME = "docpilot"
+    PROJECT_DESCRIPTION = "A local-first RAG pipeline CLI tool"
 
 @app.command()
 def project(
@@ -92,15 +99,15 @@ def generate_ascii_art() -> str:
     try:
         import pyfiglet
 
-        ascii_text = pyfiglet.figlet_format(PROJECT_NAME, font="banner")
+        ascii_text = pyfiglet.figlet_format(PROJECT_NAME, font="slant")
     except ImportError:
         # Fallback to simple ASCII if pyfiglet not available
         ascii_text = """
-    ____            ____  _ _       _   
-   / __ \\___  _____/ __ \\(_) |     | |  
-  / / / / _ \\/ ___/ /_/ / /| |     | |  
- / /_/ /  __/ /__/ ____/ / | |___  |_|  
-/_____/\\___/\\___/_/   /_/  |_____/  (_) 
+    ____             ____  _ __      __ 
+   / __ \\____  _____/ __ \\(_) /___  / / 
+  / / / / __ \\/ ___/ /_/ / / / __ \\/ /  
+ / /_/ / /_/ / /__/ ____/ / / /_/ / /   
+/_____/\\____/\\___/_/   /_/_/\\____/_/    
 """
     return ascii_text
 
@@ -109,11 +116,16 @@ def generate_ascii_art() -> str:
 def show():
     """Display version and project information in beautiful ASCII art."""
     ascii_art = generate_ascii_art()
-    print(ascii_art)
-    print("=" * 60)
-    print(f"Version:     {PROJECT_VERSION}")
-    print(f"Description: {PROJECT_DESCRIPTION}")
-    print("=" * 60)
+    console.print(f"[bold cyan]{ascii_art}[/bold cyan]")
+    
+    info_panel = Panel(
+        f"[bold]Version:[/bold]     [cyan]{PROJECT_VERSION}[/cyan]\n"
+        f"[bold]Description:[/bold] [cyan]{PROJECT_DESCRIPTION}[/cyan]",
+        border_style="cyan",
+        title="[bold green]System Info[/bold green]",
+        padding=(1, 2)
+    )
+    console.print(info_panel)
 
 
 def parse_markdown(content: str) -> None:

{docpilot_cli-1.0.2 → docpilot_cli-1.0.3}/src/docpilot_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docpilot-cli
-Version: 1.0.2
+Version: 1.0.3
 Summary: A local-first RAG pipeline CLI tool
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -59,9 +59,11 @@ pip install "docpilot-cli[pdf]"
 ```
 
 ### Prerequisites
+
 1. **Python 3.12+**
 2. **[Ollama](https://ollama.com/)**: Installed and running in the background.
 3. Pull your preferred models:
+
 ```bash
 ollama pull qwen2.5:latest
 ollama pull mxbai-embed-large:335m
@@ -71,9 +73,10 @@ ollama pull mxbai-embed-large:335m
 
 ## 🛠️ Quick Start
 
-The very first time you run a DocPilot command, it will launch the **Interactive Setup Wizard** to help you configure your chat and embedding models. 
+The very first time you run a DocPilot command, it will launch the **Interactive Setup Wizard** to help you configure your chat and embedding models.
 
 ### 1. Ingest Knowledge
+
 Point DocPilot to any documentation site, sitemap, PDF, or CSV:
 
 ```bash
@@ -91,6 +94,7 @@ docpilot ingest "./data/faq.csv"
 > If you installed via standard `pip` and get a "command not found" error because your binary path isn't configured, you can always run docpilot by prefixing commands with `python -m docpilot` (e.g., `python -m docpilot ingest ...`).
 
 ### 2. Ask Questions
+
 Query your newly created local knowledge base:
 
 ```bash
@@ -104,26 +108,34 @@ docpilot ask "How do I create a virtual environment?"
 Manage your configuration, models, and local database with ease.
 
 ### `docpilot setup`
+
 Re-run the interactive setup wizard at any time to change your default models.
 
 ### `docpilot project`
+
 Switch to a different project or check the active project. Each project has its own isolated vector database.
+
 ```bash
 docpilot project
 docpilot project <project-name>
 ```
 
 ### `docpilot clear`
+
 Wipe your local Chroma vector database to start fresh. Prompts for safety confirmation.
 
 ### `docpilot speed [profile]`
+
 Adjust the retrieval and generation settings for your desired use case.
+
 - `fast`: Lower latency, shorter context limits.
 - `balanced`: Default trade-off.
 - `quality`: Larger context, more comprehensive answers, slower inference.
 
 ### `docpilot model`
+
 Manually manage your Ollama models without the interactive setup wizard.
+
 ```bash
 docpilot model list
 docpilot model set <chat-model>
@@ -131,9 +143,11 @@ docpilot model setembed <embedding-model>
 ```
 
 ### `docpilot render`
+
 Parse and beautifully render any markdown file or text string directly in your terminal.
 
 ### `docpilot show`
+
 Display your current project version and configuration in beautiful ASCII art.
 
 ---
@@ -156,6 +170,7 @@ DocPilot employs an optimized RAG (Retrieval-Augmented Generation) pipeline:
 Contributions are welcome! If you are using DocPilot for your daily workflows or in a hackathon, feel free to open issues and pull requests.
 
 To set up a local development environment:
+
 ```bash
 git clone https://github.com/yourusername/docpilot.git
 cd docpilot