Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Response parsing should accommodate JSONL responses #20

Open
matthewmcneely opened this issue Dec 4, 2024 · 0 comments · May be fixed by #21
Open

Response parsing should accommodate JSONL responses #20

matthewmcneely opened this issue Dec 4, 2024 · 0 comments · May be fixed by #21

Comments

@matthewmcneely
Copy link

Ollama (and other) LLMs return JSONL responses. For example:

{"model":"qwen2.5-coder:32b","created_at":"2024-12-04T01:02:49.430146Z","response":"{\"","done":false}
{"model":"qwen2.5-coder:32b","created_at":"2024-12-04T01:02:49.547325Z","response":"tool","done":false}
<snip>
"model":"qwen2.5-coder:32b","created_at":"2024-12-04T01:02:51.164084Z","response":"","done":true,"done_reason":"stop","context":[<snip>],"total_duration":4234087125,"load_duration":9450125,"prompt_eval_count":279,"prompt_eval_duration":2489000000,"eval_count":16,"eval_duration":1734000000}

The attemptGenerate function of LLMImpl fails to handle this gracefully, resulting in warnings for every invocation to Ollama.

@matthewmcneely matthewmcneely linked a pull request Dec 4, 2024 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant