Adam McQuilkin commited on
Commit
6033d24
·
1 Parent(s): 451b0cb

Default readme remote options to closed (#28)

Browse files
Files changed (1) hide show
  1. README.md +22 -7
README.md CHANGED
@@ -14,6 +14,7 @@
14
  To install the library, simply run `pip install repo2vec`!
15
 
16
  ## Prerequisites
 
17
  `repo2vec` performs two steps:
18
 
19
  1. Indexes your codebase (requiring an embdder and a vector store)
@@ -23,6 +24,7 @@ To install the library, simply run `pip install repo2vec`!
23
  <summary><strong>:computer: Running locally</strong></summary>
24
 
25
  1. To index the codebase locally, we use the open-source project <a href="https://github.com/marqo-ai/marqo">Marqo</a>, which is both an embedder and a vector store. To bring up a Marqo instance:
 
26
  ```
27
  docker rm -f marqo
28
  docker pull marqoai/marqo:latest
@@ -33,6 +35,7 @@ To install the library, simply run `pip install repo2vec`!
33
 
34
  - Head over to [ollama.com](https://ollama.com) to download the appropriate binary for your machine.
35
  - Pull the desired model, e.g. `ollama pull llama3.1`.
 
36
  </details>
37
 
38
  <details>
@@ -50,6 +53,7 @@ To install the library, simply run `pip install repo2vec`!
50
  ```
51
  export ANTHROPIC_API_KEY=...
52
  ```
 
53
  </details>
54
 
55
  <br>
@@ -59,6 +63,7 @@ If you are planning on indexing GitHub issues in addition to the codebase, you w
59
  export GITHUB_TOKEN=...
60
 
61
  ## Running it
 
62
  <details open>
63
  <summary><strong>:computer: Running locally</strong></summary>
64
  <p>To index the codebase:</p>
@@ -77,7 +82,7 @@ If you are planning on indexing GitHub issues in addition to the codebase, you w
77
  --llm-model=llama3.1
78
  </details>
79
 
80
- <details open>
81
  <summary><strong>:cloud: Using external providers</strong></summary>
82
  <p>To index the codebase:</p>
83
 
@@ -98,25 +103,35 @@ To get a public URL for your chat app, set `--share=true`.
98
  </details>
99
 
100
  ## Additional features
 
101
  - **Control which files get indexed** based on their extension. You can whitelist or blacklist extensions by passing a file with one extension per line (in the format `.ext`):
102
- - To only index a whitelist of files:
 
103
  ```
104
  index ... --include=/path/to/extensions/file
105
  ```
106
- - To index all code except a blacklist of files:
 
 
107
  ```
108
  index ... --exclude=/path/to/extensions/file
109
  ```
 
110
  - **Index open GitHub issues** (remember to `export GITHUB_TOKEN=...`):
111
- - To index GitHub issues without comments:
 
112
  ```
113
  index ... --index-issues
114
  ```
115
- - To index GitHub issues with comments:
 
 
116
  ```
117
  index ... --index-issues --index-issue-comments
118
  ```
119
- - To index GitHub issues, but not the codebase:
 
 
120
  ```
121
  index ... --index-issues --no-index-repo
122
  ```
@@ -153,4 +168,4 @@ If you're the maintainer of an OSS repo and would like a dedicated page on Code
153
 
154
  We built the code purposefully modular so that you can plug in your desired embeddings, LLM and vector stores providers by simply implementing the relevant abstract classes.
155
 
156
- Feel free to send feature requests to [founders@storia.ai](mailto:founders@storia.ai) or make a pull request!
 
14
  To install the library, simply run `pip install repo2vec`!
15
 
16
  ## Prerequisites
17
+
18
  `repo2vec` performs two steps:
19
 
20
  1. Indexes your codebase (requiring an embdder and a vector store)
 
24
  <summary><strong>:computer: Running locally</strong></summary>
25
 
26
  1. To index the codebase locally, we use the open-source project <a href="https://github.com/marqo-ai/marqo">Marqo</a>, which is both an embedder and a vector store. To bring up a Marqo instance:
27
+
28
  ```
29
  docker rm -f marqo
30
  docker pull marqoai/marqo:latest
 
35
 
36
  - Head over to [ollama.com](https://ollama.com) to download the appropriate binary for your machine.
37
  - Pull the desired model, e.g. `ollama pull llama3.1`.
38
+
39
  </details>
40
 
41
  <details>
 
53
  ```
54
  export ANTHROPIC_API_KEY=...
55
  ```
56
+
57
  </details>
58
 
59
  <br>
 
63
  export GITHUB_TOKEN=...
64
 
65
  ## Running it
66
+
67
  <details open>
68
  <summary><strong>:computer: Running locally</strong></summary>
69
  <p>To index the codebase:</p>
 
82
  --llm-model=llama3.1
83
  </details>
84
 
85
+ <details>
86
  <summary><strong>:cloud: Using external providers</strong></summary>
87
  <p>To index the codebase:</p>
88
 
 
103
  </details>
104
 
105
  ## Additional features
106
+
107
  - **Control which files get indexed** based on their extension. You can whitelist or blacklist extensions by passing a file with one extension per line (in the format `.ext`):
108
+ - To only index a whitelist of files:
109
+
110
  ```
111
  index ... --include=/path/to/extensions/file
112
  ```
113
+
114
+ - To index all code except a blacklist of files:
115
+
116
  ```
117
  index ... --exclude=/path/to/extensions/file
118
  ```
119
+
120
  - **Index open GitHub issues** (remember to `export GITHUB_TOKEN=...`):
121
+ - To index GitHub issues without comments:
122
+
123
  ```
124
  index ... --index-issues
125
  ```
126
+
127
+ - To index GitHub issues with comments:
128
+
129
  ```
130
  index ... --index-issues --index-issue-comments
131
  ```
132
+
133
+ - To index GitHub issues, but not the codebase:
134
+
135
  ```
136
  index ... --index-issues --no-index-repo
137
  ```
 
168
 
169
  We built the code purposefully modular so that you can plug in your desired embeddings, LLM and vector stores providers by simply implementing the relevant abstract classes.
170
 
171
+ Feel free to send feature requests to [founders@storia.ai](mailto:founders@storia.ai) or make a pull request!