readme update

readme update

CONFIGURATION.md

@@ -1,16 +1,16 @@
 ## Configuration
 
-The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the configuration file: `/pr-agent/settings/configuration.toml`.
+The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](pr_agent/settings/configuration.toml)**
 
-### CLI
+### Working from CLI
-When running from source (CLI), your local configuration file will be used.
+When running from source (CLI), your local configuration file will be initially used.
 
 Example for invoking the 'review' tools via the CLI: 
 
 ```
 python cli.py --pr-url=<pr_url>  review
 ```
-In addition to general configurations, The 'review' tool will use parameters from the `[pr_reviewer]` section. Every tool has a dedicated section in the configuration file
+In addition to general configurations, the 'review' tool will use parameters from the `[pr_reviewer]` section (every tool has a dedicated section in the configuration file).
 
 Note that you can print results locally, without publishing them, by setting in `configuration.toml`:
 
@@ -21,14 +21,37 @@ verbosity_level=2
 ```
 This is useful for debugging or experimenting with the different tools.
 
-### Working from pre-built repo (GitHub Action/GitHub App/Docker/...)
+### Working from pre-built repo (GitHub Action/GitHub App/Docker)
 When running PR-Agent from a pre-built repo, the default configuration file will be loaded.
 
-To edit the configuration of any tool, just add `--config_path=<value>` to you command.
+To edit the configuration, you have two options: 
-For example if you want to edit online `pr_reviewer` configurations, you can run:
+1. Place a local configuration file in the root of your local repo. The local file will be used instead of the default one.
+2. For online usage, just add `--config_path=<value>` to you command, to edit a specific configuration value.
+For example if you want to edit `pr_reviewer` configurations, you can run:
 ```
-/review --pr_reviewer.extra_instructions="focus on the file xyz" --pr_reviewer.require_score_review=false ...
+/review --pr_reviewer.extra_instructions="..." --pr_reviewer.require_score_review=false ...
 ```
 
 Any configuration value in `configuration.toml` file can be similarly edited.
 
+### General configuration parameters
+
+#### Changing a model
+See [here](pr_agent/algo/__init__.py) for the list of available models.
+
+To use Llama2 model, for example, set:
+```
+[config]
+model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
+[replicate]
+key = ...
+```
+(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
+
+Also review the [AiHandler](pr_agent/algo/ai_handler.py) file for instruction how to set keys for other models.
+
+#### Extra instructions
+All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
+```
+/update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
+```

README.md

@@ -93,6 +93,7 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 | CORE  | PR compression                              |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
 |       | Repo language prioritization                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
 |       | Adaptive and token-aware<br />file patch fitting |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | Multiple models support |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
 |       | Incremental PR Review |   :white_check_mark:    |      |         |
 
 Examples for invoking the different tools via the CLI:
@@ -152,24 +153,23 @@ Here are some advantages of PR-Agent:
 - We emphasize **real-life practical usage**. Each tool (review, improve, ask, ...) has a single GPT-4 call, no more. We feel that this is critical for realistic team usage - obtaining an answer quickly (~30 seconds) and affordably.
 - Our [PR Compression strategy](./PR_COMPRESSION.md)  is a core ability that enables to effectively tackle both short and long PRs.
 - Our JSON prompting strategy enables to have **modular, customizable tools**. For example, the '/review' tool categories can be controlled via the [configuration](./CONFIGURATION.md) file. Adding additional categories is easy and accessible.
-- We support **multiple git providers** (GitHub, Gitlab, Bitbucket), and multiple ways to use the tool (CLI, GitHub Action, GitHub App, Docker, ...).
+- We support **multiple git providers** (GitHub, Gitlab, Bitbucket), **multiple ways** to use the tool (CLI, GitHub Action, GitHub App, Docker, ...), and **multiple models** (GPT-4, GPT-3.5, Anthropic, Cohere, Llama2).
 - We are open-source, and welcome contributions from the community.
 
 
 ## Roadmap
 
-- [ ] Support open-source models, as a replacement for OpenAI models. (Note - a minimal requirement for each open-source model is to have 8k+ context, and good support for generating JSON as an output)
+- [x] Support additional models, as a replacement for OpenAI (see [here](https://github.com/Codium-ai/pr-agent/pull/172))
-- [x] Support other Git providers, such as Gitlab and Bitbucket.
+- [ ] Develop additional logic for handling large PRs
-- [ ] Develop additional logic for handling large PRs, and compressing git patches
 - [ ] Add additional context to the prompt. For example, repo (or relevant files) summarization, with tools such a [ctags](https://github.com/universal-ctags/ctags)
 - [ ] Adding more tools. Possible directions:
   - [x] PR description
   - [x] Inline code suggestions
   - [x] Reflect and review
+  - [x] Rank the PR (see [here](https://github.com/Codium-ai/pr-agent/pull/89))   
   - [ ] Enforcing CONTRIBUTING.md guidelines
   - [ ] Performance (are there any performance issues)
   - [ ] Documentation (is the PR properly documented)
-  - [ ] Rank the PR importance
   - [ ] ...
 
 ## Similar Projects