Simplify name to "Sage" (#35)

.gitignore

@@ -3,4 +3,4 @@ __pycache__
 *.cpython.*
 build/
 repos/
-codesage.egg-info/
+sage.egg-info/

MANIFEST.in

@@ -1 +1 @@
-include codesage/sample-exclude.txt
+include sage/sample-exclude.txt

README.md

@@ -1,13 +1,14 @@
 <div align="center">
-    <h1 align="center">Code Sage</h1>
-    <p align="center">An open-source pair programmer for chatting with any codebase.</p>
+    <img src="assets/storia-logo.png" alt="Logo" width="50" style="border-radius: 15px;">
+    <h1 align="center">Sage: Chat with any codebase</h1>
     <div>
-        <img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/Storia-AI/CodeSage?logo=github" />
-        <img alt="GitHub License" src="https://img.shields.io/github/license/Storia-AI/CodeSage"></img>
+        <img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/Storia-AI/sage?logo=github" />
+        <img alt="GitHub License" src="https://img.shields.io/github/license/Storia-AI/sage"></img>
         <a href="https://x.com/StoriaAI">
             <img alt="X (formerly Twitter) Follow" src="https://img.shields.io/twitter/follow/StoriaAI"></img>
         </a>
     </div>
+    <br />
     <figure>
         <!-- The <kbd> and <sub> tags are work-arounds for styling, since GitHub doesn't take into account inline styles. Note it might display awkwardly on other Markdown editors. -->
         <kbd><img src="assets/chat_screenshot2.png" alt="screenshot" /></kbd>
@@ -24,7 +25,7 @@
 Make sure pipx is installed on your system (see <a href="https://pipx.pypa.io/stable/installation/">instructions</a>), then run:
 
 ```
-pipx install git+https://github.com/Storia-AI/CodeSage.git@main
+pipx install git+https://github.com/Storia-AI/sage.git@main
 ```
 
 </details>
@@ -34,16 +35,16 @@ pipx install git+https://github.com/Storia-AI/CodeSage.git@main
 Alternatively, you can manually create a virtual environment and install Code Sage via pip:
 
 ```
-python -m venv codesage-venv
-source codesage-venv/bin/activate
-pip install git+https://github.com/Storia-AI/CodeSage.git@main
+python -m venv sage-venv
+source sage-venv/bin/activate
+pip install git+https://github.com/Storia-AI/sage.git@main
 ```
 
 </details>
 
 ## Prerequisites
 
-`codesage` performs two steps:
+`sage` performs two steps:
 
 1. Indexes your codebase (requiring an embdder and a vector store)
 2. Enables chatting via LLM + RAG (requiring access to an LLM)
@@ -110,12 +111,12 @@ If you are planning on indexing GitHub issues in addition to the codebase, you w
 
 2. Index the repository. This might take a few minutes, depending on its size.
     ```
-    cs-index $GITHUB_REPO
+    sage-index $GITHUB_REPO
     ```
 
 3. Chat with the repository, once it's indexed:
     ```
-    cs-chat $GITHUB_REPO
+    sage-chat $GITHUB_REPO
     ```
     To get a public URL for your chat app, set `--share=true`.
 
@@ -131,7 +132,7 @@ If you are planning on indexing GitHub issues in addition to the codebase, you w
 
 2. Index the repository. This might take a few minutes, depending on its size.
     ```
-    cs-index $GITHUB_REPO \
+    sage-index $GITHUB_REPO \
         --embedder-type=openai \
         --vector-store=pinecone \
         --index-name=$PINECONE_INDEX_NAME
@@ -139,7 +140,7 @@ If you are planning on indexing GitHub issues in addition to the codebase, you w
 
 3. Chat with the repository, once it's indexed:
     ```
-    cs-chat $GITHUB_REPO \
+    sage-chat $GITHUB_REPO \
         --vector-store-type=pinecone \
         --index-name=$PINECONE_INDEX_NAME \
         --llm-provider=openai \
@@ -173,14 +174,14 @@ where:
 
 To specify an inclusion file (i.e. only index the specified files):
 ```
-cs-index $GITHUB_REPO --include=/path/to/inclusion/file
+sage-index $GITHUB_REPO --include=/path/to/inclusion/file
 ```
 
 To specify an exclusion file (i.e. index all files, except for the ones specified):
 ```
-cs-index $GITHUB_REPO --exclude=/path/to/exclusion/file
+sage-index $GITHUB_REPO --exclude=/path/to/exclusion/file
 ```
-By default, we use the exclusion file [sample-exclude.txt](codesage/sample-exclude.txt).
+By default, we use the exclusion file [sample-exclude.txt](sage/sample-exclude.txt).
 </details>
 
 <details>
@@ -192,17 +193,17 @@ export GITHUB_TOKEN=...
 
 To index GitHub issues without comments:
 ```
-cs-index $GITHUB_REPO --index-issues
+sage-index $GITHUB_REPO --index-issues
 ```
 
 To index GitHub issues with comments:
 ```
-cs-index $GITHUB_REPO --index-issues --index-issue-comments
+sage-index $GITHUB_REPO --index-issues --index-issue-comments
 ```
 
 To index GitHub issues, but not the codebase:
 ```
-cs-index $GITHUB_REPO --index-issues --no-index-repo
+sage-index $GITHUB_REPO --index-issues --no-index-repo
 ```
 </details>
 
@@ -211,7 +212,7 @@ cs-index $GITHUB_REPO --index-issues --no-index-repo
 Sometimes you just want to learn how a codebase works and how to integrate it, without spending hours sifting through
 the code itself.
 
-`codesage` is like an open-source GitHub Copilot with the most up-to-date information about your repo.
+`sage` is like an open-source GitHub Copilot with the most up-to-date information about your repo.
 
 Features:
 
@@ -222,7 +223,7 @@ Features:
 
 # Changelog
 
-- 2024-09-16: Renamed `repo2vec` to `codesage`.
+- 2024-09-16: Renamed `repo2vec` to `sage`.
 - 2024-09-03: Support for indexing GitHub issues.
 - 2024-08-30: Support for running everything locally (Marqo for embeddings, Ollama for LLMs).
 

{codesage → sage}/chat.py

@@ -12,8 +12,8 @@ from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain.schema import AIMessage, HumanMessage
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 
-import codesage.vector_store as vector_store
-from codesage.llm import build_llm_via_langchain
+import sage.vector_store as vector_store
+from sage.llm import build_llm_via_langchain
 
 load_dotenv()
 

{codesage → sage}/data_manager.py

@@ -35,7 +35,7 @@ class GitHubRepoManager(DataManager):
     ):
         """
         Args:
-            repo_id: The identifier of the repository in owner/repo format, e.g. "Storia-AI/codesage".
+            repo_id: The identifier of the repository in owner/repo format, e.g. "Storia-AI/sage".
             local_dir: The local directory where the repository will be cloned.
             inclusion_file: A file with a lists of files/directories/extensions to include. Each line must be in one of
                 the following formats: "ext:.my-extension", "file:my-file.py", or "dir:my-directory".

{codesage → sage}/embedder.py

@@ -11,8 +11,8 @@ from typing import Dict, Generator, List, Optional, Tuple
 import marqo
 from openai import OpenAI
 
-from codesage.chunker import Chunk, Chunker
-from codesage.data_manager import DataManager
+from sage.chunker import Chunk, Chunker
+from sage.data_manager import DataManager
 
 Vector = Tuple[Dict, List[float]]  # (metadata, embedding)
 

{codesage → sage}/github.py

@@ -8,8 +8,8 @@ from typing import Any, Dict, Generator, List, Tuple
 import requests
 import tiktoken
 
-from codesage.chunker import Chunk, Chunker
-from codesage.data_manager import DataManager
+from sage.chunker import Chunk, Chunker
+from sage.data_manager import DataManager
 
 tokenizer = tiktoken.get_encoding("cl100k_base")
 

{codesage → sage}/index.py

@@ -7,11 +7,11 @@ import time
 
 import pkg_resources
 
-from codesage.chunker import UniversalFileChunker
-from codesage.data_manager import GitHubRepoManager
-from codesage.embedder import build_batch_embedder_from_flags
-from codesage.github import GitHubIssuesChunker, GitHubIssuesManager
-from codesage.vector_store import build_from_args
+from sage.chunker import UniversalFileChunker
+from sage.data_manager import GitHubRepoManager
+from sage.embedder import build_batch_embedder_from_flags
+from sage.github import GitHubIssuesChunker, GitHubIssuesManager
+from sage.vector_store import build_from_args
 
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger()

setup.py

@@ -7,18 +7,18 @@ def readfile(filename):
 
 
 setup(
-    name="codesage",
+    name="sage",
     version="0.1.0",
     packages=find_packages(),
     include_package_data=True,
     package_data={
-        "codesage": ["sample-exclude.txt"],
+        "sage": ["sample-exclude.txt"],
     },
     install_requires=open("requirements.txt").readlines() + ["setuptools"],
     entry_points={
         "console_scripts": [
-            "cs-index=codesage.index:main",
-            "cs-chat=codesage.chat:main",
+            "sage-index=sage.index:main",
+            "sage-chat=sage.chat:main",
         ],
     },
     author="Julia Turc & Mihail Eric / Storia AI",
@@ -26,7 +26,7 @@ setup(
     description="A library to index a code repository and chat with it via LLMs.",
     long_description=open("README.md").read(),
     long_description_content_type="text/markdown",
-    url="https://github.com/Storia-AI/codesage",
+    url="https://github.com/Storia-AI/sage",
     classifiers=[
         "Programming Language :: Python :: 3",
         "License :: OSI Approved :: MIT License",

tests/conftest.py

@@ -1,4 +1,4 @@
 import os
 import sys
 
-sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../codesage")))
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../sage")))

tests/test_chunker.py

@@ -11,12 +11,12 @@ import os
 
 from pytest import mark, param
 
-import codesage.chunker
+import sage.chunker
 
 
 def test_text_chunker_happy_path():
     """Tests the happy path for the TextFileChunker."""
-    chunker = codesage.chunker.TextFileChunker(max_tokens=100)
+    chunker = sage.chunker.TextFileChunker(max_tokens=100)
 
     file_path = os.path.join(os.path.dirname(__file__), "../README.md")
     with open(file_path, "r") as file:
@@ -29,9 +29,9 @@ def test_text_chunker_happy_path():
 
 def test_code_chunker_happy_path():
     """Tests the happy path for the CodeFileChunker."""
-    chunker = codesage.chunker.CodeFileChunker(max_tokens=100)
+    chunker = sage.chunker.CodeFileChunker(max_tokens=100)
 
-    file_path = os.path.join(os.path.dirname(__file__), "../codesage/chunker.py")
+    file_path = os.path.join(os.path.dirname(__file__), "../sage/chunker.py")
     with open(file_path, "r") as file:
         content = file.read()
     metadata = {"file_path": file_path}
@@ -48,22 +48,22 @@ def test_code_chunker_typescript(filename):
         content = file.read()
     metadata = {"file_path": file_path}
 
-    chunker = codesage.chunker.CodeFileChunker(max_tokens=100)
+    chunker = sage.chunker.CodeFileChunker(max_tokens=100)
     chunks = chunker.chunk(content, metadata)
     # There's a bug in the tree-sitter-language-pack library for TypeScript. Before it gets fixed, we expect this to
     # return an empty list (instead of crashing).
     assert len(chunks) == 0
 
     # However, the UniversalFileChunker should fallback onto a regular text chunker, and return some chunks.
-    chunker = codesage.chunker.UniversalFileChunker(max_tokens=100)
+    chunker = sage.chunker.UniversalFileChunker(max_tokens=100)
     chunks = chunker.chunk(content, metadata)
     assert len(chunks) >= 1
 
 
 def test_ipynb_chunker_happy_path():
     """Tests the happy path for the IPynbChunker."""
-    code_chunker = codesage.chunker.CodeFileChunker(max_tokens=100)
-    chunker = codesage.chunker.IpynbFileChunker(code_chunker)
+    code_chunker = sage.chunker.CodeFileChunker(max_tokens=100)
+    chunker = sage.chunker.IpynbFileChunker(code_chunker)
 
     file_path = os.path.join(os.path.dirname(__file__), "assets/sample-notebook.ipynb")
     with open(file_path, "r") as file: