From 751edfefe5e868b7cd9c7f7ee193ec7ea9a64df4 Mon Sep 17 00:00:00 2001
From: Saba <narmiabas@gmail.com>
Date: Tue, 13 Jun 2023 16:55:58 -0700
Subject: [PATCH] Add separate unit test for github. Will only run of a PAT
 token is set

---
 README.md                 |  7 ++++++-
 tests/conftest.py         | 10 ++++++++++
 tests/test_text_search.py | 13 +++++++++++++
 3 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 5e8feb45..96aebc6c 100644
--- a/README.md
+++ b/README.md
@@ -328,6 +328,11 @@ Add your OpenAI API to Khoj by using either of the two options below:
   1. [Setup your OpenAI API key in Khoj](#set-your-openai-api-key-in-khoj)
   2. Interact with them from the [Khoj Swagger docs](http://locahost:8000/docs)[^2]
 
+### Use a Github Repository as a source
+Note that this plugin is currently *only* indexing Markdown files. It will ignore all other files in the repository. This is because Khoj, as it stands, is a semantic search engine. Eventually, we hope to get to a state where you can search for any file in your repository and even explain code.
+
+1. Get a [pat token](https://docs.github.com/en/github/authenticating-to-github/keeping-your-account-and-data-secure/creating-a-personal-access-token) with `repo` and `read:org` scopes in the classic flow.
+2. Configure your settings to include the `owner` and `repo_name`. The `owner` will be the organization name if the repo is in an organization. The `repo_name` will be the name of the repository. Optionally, you can also supply a branch name. If no branch name is supplied, the `master` branch will be used.
 
 ## Performance
 
@@ -458,7 +463,7 @@ conda activate khoj
 
 #### Before Creating PR
 
-1. Run Tests
+1. Run Tests. If you get an error complaining about a missing `fast_tokenizer_file`, follow the solution [in this Github issue](https://github.com/UKPLab/sentence-transformers/issues/1659).
    ```shell
    pytest
    ```
diff --git a/tests/conftest.py b/tests/conftest.py
index 6ef2394f..e061f279 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -16,6 +16,7 @@ from khoj.utils.rawconfig import (
     ConversationProcessorConfig,
     ProcessorConfig,
     TextContentConfig,
+    GithubContentConfig,
     ImageContentConfig,
     SearchConfig,
     TextSearchConfig,
@@ -89,6 +90,15 @@ def content_config(tmp_path_factory, search_config: SearchConfig):
         )
     }
 
+    content_config.github = GithubContentConfig(
+        pat_token=os.getenv("GITHUB_PAT_TOKEN"),
+        repo_name="lantern",
+        repo_owner="khoj-ai",
+        repo_branch="master",
+        compressed_jsonl=content_dir.joinpath("github.jsonl.gz"),
+        embeddings_file=content_dir.joinpath("github_embeddings.pt"),
+    )
+
     filters = [DateFilter(), WordFilter(), FileFilter()]
     text_search.setup(
         JsonlToJsonl, content_config.plugins["plugin1"], search_config.asymmetric, regenerate=False, filters=filters
diff --git a/tests/test_text_search.py b/tests/test_text_search.py
index 830feb9b..6eecac07 100644
--- a/tests/test_text_search.py
+++ b/tests/test_text_search.py
@@ -1,6 +1,7 @@
 # System Packages
 import logging
 from pathlib import Path
+import os
 
 # External Packages
 import pytest
@@ -10,6 +11,7 @@ from khoj.utils.state import model
 from khoj.search_type import text_search
 from khoj.utils.rawconfig import ContentConfig, SearchConfig, TextContentConfig
 from khoj.processor.org_mode.org_to_jsonl import OrgToJsonl
+from khoj.processor.github.github_to_jsonl import GithubToJsonl
 
 
 # Test
@@ -170,3 +172,14 @@ def test_incremental_update(content_config: ContentConfig, search_config: Search
     # Cleanup
     # reset input_files in config to empty list
     content_config.org.input_files = []
+
+
+# ----------------------------------------------------------------------------------------------------
+@pytest.mark.skipif(os.getenv("GITHUB_PAT_TOKEN") is None, reason="GITHUB_PAT_TOKEN not set")
+def test_asymmetric_setup_github(content_config: ContentConfig, search_config: SearchConfig):
+    # Act
+    # Regenerate notes embeddings during asymmetric setup
+    github_model = text_search.setup(GithubToJsonl, content_config.github, search_config.asymmetric, regenerate=True)
+
+    # Assert
+    assert len(github_model.entries) > 1