You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+11Lines changed: 11 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,16 @@
1
1
# Changelog
2
2
3
+
## [v0.5.0] - 2025-10-27
4
+
5
+
- Bump `pipelex` to `v0.14.0`: See `Pipelex` changelog [here](https://docs.pipelex.com/changelog/)
6
+
7
+
### Changed
8
+
- Documentation Improvements: Overhauled `README.md` with a new "Get Your API Keys" section outlining three configuration methods (free `PIPELEX_API_KEY`, bring-your-own provider keys, or local AI models). Updated terminology from "AI-powered pipelines" to "AI-powered workflows".
9
+
10
+
### Removed
11
+
- Removed unused `is_activity_tracking_enabled` option from `pipelex.toml` configuration files.
12
+
- Removed `reportConstantRedescription` and `reportShadowedImports` linter rules from `pyproject.toml`.
Copy file name to clipboardExpand all lines: README.md
+32-8Lines changed: 32 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
*Cocode is the friend of your code*
4
4
5
-
Cocode is a powerful command-line tool for analyzing and processing code repositories. It converts repository structures and contents into text formats, extracts code interfaces, and performs software engineering analysis using **AI-powered pipelines** using [Pipelex](https://github.com/Pipelex/pipelex).
5
+
Cocode is a powerful command-line tool for analyzing and processing code repositories. It converts repository structures and contents into text formats, extracts code interfaces, and performs software engineering analysis using **AI-powered workflows** using [Pipelex](https://github.com/Pipelex/pipelex).
6
6
7
7
<h3align="center">Cocode demo</h3>
8
8
<palign="center">
@@ -25,18 +25,42 @@ pip install cocode
25
25
26
26
Important: the current version of Cocode only works when run from the cocode directory.
27
27
28
+
## 🔑 Get Your API Keys
29
+
30
+
Cocode's built-in AI workflows require access to AI models. To use the main features (changelog generation, documentation updates, proofreading), you need API keys for:
31
+
32
+
-**Claude models** (Anthropic) - Required for changelog generation and documentation analysis
33
+
-**Gemini models** (Google) - Required for documentation proofreading
34
+
35
+
You have several options:
36
+
37
+
### Option 1: Free Pipelex API Key (Free)
38
+
Get free access to all models with a single API key:
- Request your **free API key** (no credit card required) in the [🔑・free-api-key](https://discord.com/channels/1369447918955921449/1418228010431025233) channel
41
+
- Add it to your `.env` file: `PIPELEX_API_KEY=your-key-here`
42
+
43
+
### Option 2: Bring Your Own API Keys
44
+
Use your own API keys from AI providers:
45
+
46
+
**Required for core features:**
47
+
- Claude models - Use either:
48
+
-`ANTHROPIC_API_KEY` - Direct Anthropic API ([Get key](https://console.anthropic.com/))
49
+
- Amazon Bedrock - AWS credentials for Claude via Bedrock ([Setup guide](https://docs.pipelex.com/pages/configuration/config-technical/inference-backend-config/))
50
+
- Google Cloud credentials - For Gemini models ([Setup guide](https://docs.pipelex.com/pages/build-reliable-ai-workflows-with-pipelex/ai-plugins-for-multi-llm-workflows/#4-google-vertex-ai-configuration))
51
+
52
+
Add these to your environment variables or in your `.env` file in your project root.
53
+
54
+
### Option 3: Local AI
55
+
You can also use local models with Ollama, vLLM, or any OpenAI-compatible endpoint. See the [Pipelex configuration guide](https://docs.pipelex.com/pages/setup/configure-ai-providers/) for details.
56
+
28
57
## ✅ Validation
29
58
30
59
```bash
31
60
# Verify setup and pipelines
32
61
cocode validate
33
62
```
34
63
35
-
### Set up environment variables
36
-
37
-
Enter your API keys into your `.env` file. The `OPENAI_API_KEY` is enough to get you started, but some pipelines require models from other providers.
38
-
Some complex pipelines require GCP credentials (See [GCP credentials](https://docs.pipelex.com/pages/build-reliable-ai-workflows-with-pipelex/ai-plugins-for-multi-llm-workflows/#4-google-vertex-ai-configuration) for more details), or Anthropic API keys `ANTHROPIC_API_KEY`.
39
-
40
64
## 🛠️ Quick Start
41
65
42
66
### Automatic Documentation & Release Features
@@ -45,10 +69,10 @@ Some complex pipelines require GCP credentials (See [GCP credentials](https://do
0 commit comments