Commit graph

177 commits

Author SHA1 Message Date
Paul Gauthier
72613f3b27 switch naming from openai/gpt-4o to gpt-4o 2024-05-15 06:25:30 -07:00
Paul Gauthier
bfba56c5f1 added 4o as default 2024-05-13 10:57:26 -07:00
Paul Gauthier
b6cd852124 added openai/ prefix 2024-05-13 10:36:07 -07:00
Paul Gauthier
7b19f767fc Added gpt-4o 2024-05-13 10:33:08 -07:00
Paul Gauthier
b58df9c16b no ex_sys for opus 2024-05-08 16:09:18 -07:00
Paul Gauthier
c415e6f775 opus with examples_as_sys_msg 2024-05-08 15:49:53 -07:00
Paul Gauthier
5c4bc5b7ba oops 2024-05-08 15:25:55 -07:00
Paul Gauthier
bf09bd348f 0125 with ex_as_sys 2024-05-08 15:14:37 -07:00
Paul Gauthier
a9d9c6881d added gpt-3.5-turbo as explicit model 2024-05-08 13:52:20 -07:00
Paul Gauthier
9ff6770a04 refactored litellm to avoid duplicating workarounds 2024-05-08 08:05:15 -07:00
Paul Gauthier
b249177119 added settings for deepseek/deepseek-chat 2024-05-08 07:13:13 -07:00
Paul Gauthier
e9da4016c8 deepseek-chat with sys examples and sys reminder 2024-05-07 08:48:49 -07:00
Paul Gauthier
c9dbca9d0e gpt-4-0314 with examples as sys 2024-05-04 07:52:22 -07:00
Paul Gauthier
471d637694 updated llama3 2024-05-03 15:31:20 -07:00
Paul Gauthier
b5bb453378 examples_as_sys_msg 2024-05-03 15:24:36 -07:00
Paul Gauthier
f115236801 llama reminder_as_sys_msg=True 2024-05-03 15:11:22 -07:00
Paul Gauthier
5d32dd77fc Added diff-fenced coder 2024-05-03 13:50:15 -07:00
Paul Gauthier
921c7ceb80 Merge branch 'main' into gemini-editblock-and-examples 2024-05-03 13:17:23 -07:00
Paul Gauthier
e76d1c0cfa accepts_multi_system_msgs -> reminder_as_sys_msg 2024-05-01 10:30:41 -07:00
Paul Gauthier
050d35790e added /models cmd 2024-04-30 16:02:38 -07:00
Paul Gauthier
d38a38f0dd implemented accepts_multi_system_msgs 2024-04-30 07:57:29 -07:00
Paul Gauthier
2d16ee16ac Make lazy prompt configurable 2024-04-30 07:45:16 -07:00
Paul Gauthier
f9e122b9d7 Added --show-model-warnings 2024-04-23 12:15:37 -07:00
Paul Gauthier
01cf038bb5 Quiet litellm 2024-04-23 10:37:43 -07:00
Paul Gauthier
f92aecbf7a Allow repo map to work with whole edit format, for weaker models with large context 2024-04-23 10:21:54 -07:00
Paul Gauthier
341228b543 gemini benchmarked on whole so far 2024-04-23 09:53:27 -07:00
Paul Gauthier
9afa6e8435 Added gemini 1.5 pro 2024-04-23 09:49:48 -07:00
Paul Gauthier
c21118ce5c Use provider in the validate_environment workaround 2024-04-23 06:28:37 -07:00
Paul Gauthier
89a7b3470a Use fq model name in --models search 2024-04-22 19:17:27 -07:00
Paul Gauthier
25b8d6fec8 Added --models 2024-04-22 18:45:20 -07:00
Paul Gauthier
da80e6af9e Work around litellm bug 2024-04-22 15:00:53 -07:00
Paul Gauthier
6901f92f96 refac 2024-04-22 14:42:46 -07:00
Paul Gauthier
efd3c39e50 Better unknown model warnings 2024-04-22 14:09:08 -07:00
Paul Gauthier
21df025fb9 Use whole and other defaults for claude-2 2024-04-22 12:01:39 -07:00
Paul Gauthier
30c095349a Don't assume gpt-3.5-turbo as the weak model, use main_model if unsure 2024-04-22 10:57:50 -07:00
Paul Gauthier
83c76a3c65 Don't stomp Model.name after a partial match against ModelSettings #568 2024-04-22 10:36:22 -07:00
Paul Gauthier
fd5b9bbfcb Added groq llama3 2024-04-22 07:12:01 -07:00
Paul Gauthier
cd838901d1 Added improved editing support for command-r-plus 2024-04-20 16:53:27 -07:00
Paul Gauthier
9b26eeb9eb Added validate_environment=False to tests 2024-04-20 08:18:27 -07:00
Paul Gauthier
6863b47e6a Check the environment inside Model 2024-04-20 08:09:17 -07:00
Paul Gauthier
4e50f0d095 Support weak_model=False 2024-04-19 14:05:58 -07:00
Paul Gauthier
f81b62dfea Added --require-model-info 2024-04-19 14:01:02 -07:00
Paul Gauthier
aac110f078 copy 2024-04-19 13:45:51 -07:00
Paul Gauthier
6f1cebc4c2 fix: do not stomp main model.info 2024-04-19 11:24:11 -07:00
Paul Gauthier
922559a15a Refactored error handling to display model name in case of unknown model. 2024-04-19 11:17:33 -07:00
Paul Gauthier
fb3285ff77 aider: Added a main function to allow running the script with a model name from the command line and printing the results.
# Aider chat conversation:

USER: add a main func so i can run this script with a model name on the cmd line and print the results

ASSISTANT: Here are the changes to add a `main` function that allows running the script with a model name from the command line and printing the results:

aider/models.py
```python
<<<<<<< SEARCH
=======
import sys

def main():
    if len(sys.argv) != 2:
        print("Usage: python models.py <model_name>")
        sys.exit(1)

    model_name = sys.argv[1]
    matching_models = fuzzy_match_models(model_name)

    if matching_models:
        print(f"Matching models for '{model_name}':")
        for model in matching_models:
            print(model)
    else:
        print(f"No matching models found for '{model_name}'.")

if __name__ == "__main__":
    main()
>>>>>>> REPLACE
```

The `main` function does the following:

1. It checks if the script is called with exactly one command-line argument (the model name). If not, it prints the usage instructions and exits with an error code.

2. It retrieves the model name from the command-line argument using `sys.argv[1]`.

3. It calls the `fuzzy_match_models` function with the provided model name to get the list of matching models.

4. If matching models are found, it prints a message indicating the matching models for the given model name and then prints each matching model on a separate line.

5. If no matching models are found, it prints a message indicating that no matching models were found for the given model name.

The `if __name__ == "__main__":` block ensures that the `main` function is only executed when the script is run directly, not when it is imported as a module.

With these changes, you can run the script from the command line by providing a model name as an argument, and it will print the matching models or a message if no matches are found.
2024-04-19 11:08:28 -07:00
Paul Gauthier
70b2f5d054 aider: Implemented the fuzzy_match_models function to search for models containing the given name or a slight misspelling.
# Aider chat conversation:

USER: implemenet the `fuzzy_match_models` function. takes the name of a LLM like "gpt-3.5" and searches the list of `models` to find models which contain the name or contain a slight misspelling of the name

ASSISTANT: Here is an implementation of the `fuzzy_match_models` function that searches for models containing the given name or a slight misspelling:

aider/models.py
```python
<<<<<<< SEARCH
def fuzzy_match_models(name):
    models = litellm.most_cost.keys()
=======
import difflib

def fuzzy_match_models(name):
    models = litellm.most_cost.keys()

    # Check for exact match first
    if name in models:
        return [name]

    # Check for models containing the name
    matching_models = [model for model in models if name in model]

    # If no matches found, check for slight misspellings
    if not matching_models:
        matching_models = difflib.get_close_matches(name, models, n=3, cutoff=0.8)

    return matching_models
>>>>>>> REPLACE
```

This implementation does the following:

1. It first checks if the given `name` exactly matches any model in the `models` list. If an exact match is found, it returns a list containing only that model name.

2. If no exact match is found, it searches for models that contain the given `name` as a substring. It uses a list comprehension to filter the `models` list and find models that include `name`.

3. If still no matches are found, it uses the `difflib.get_close_matches()` function to find models that are close matches to the given `name`. It searches for up to 3 close matches with a similarity ratio of at least 0.8 (80%).

4. Finally, it returns the list of matching models found either by exact match, substring match, or close match.

This implementation allows for fuzzy matching of model names, considering both exact matches and slight misspellings.
2024-04-19 11:07:32 -07:00
Paul Gauthier
7ef10c56a2 Added a fuzzy model matching function to find models by name. 2024-04-19 11:07:31 -07:00
Paul Gauthier
7ec4de865d Added --weak-model 2024-04-19 10:57:21 -07:00
Paul Gauthier
93bd187bf3 Added --opus 2024-04-18 17:09:43 -07:00