Packages
fnord
0.1.0
0.9.40
0.9.39
0.9.38
0.9.37
0.9.36
0.9.35
0.9.34
0.9.33
0.9.32
0.9.31
0.9.30
0.9.29
0.9.28
0.9.27
0.9.26
0.9.25
0.9.24
0.9.23
0.9.22
0.9.21
0.9.20
0.9.19
0.9.18
0.9.17
0.9.16
0.9.15
0.9.14
0.9.13
0.9.12
0.9.11
0.9.10
0.9.9
0.9.8
0.9.7
0.9.6
0.9.5
0.9.4
0.9.3
0.9.2
0.9.1
0.9.0
0.8.99
0.8.98
0.8.97
0.8.96
0.8.95
0.8.94
0.8.93
0.8.92
0.8.91
0.8.90
0.8.89
0.8.88
0.8.87
0.8.86
0.8.85
0.8.84
0.8.83
0.8.82
0.8.81
0.8.80
0.8.79
0.8.78
0.8.77
0.8.76
0.8.75
0.8.74
0.8.73
0.8.72
0.8.71
0.8.70
0.8.69
0.8.68
0.8.67
0.8.66
0.8.65
0.8.64
0.8.63
0.8.62
0.8.61
0.8.60
0.8.59
0.8.58
0.8.57
0.8.56
0.8.55
0.8.54
0.8.53
0.8.52
0.8.51
0.8.50
0.8.49
0.8.48
0.8.47
0.8.46
0.8.45
0.8.44
0.8.43
0.8.42
0.8.41
0.8.40
0.8.39
0.8.38
0.8.37
0.8.36
0.8.35
0.8.34
0.8.33
0.8.32
0.8.31
0.8.30
0.8.29
0.8.27
0.8.26
0.8.25
0.8.24
0.8.23
0.8.22
0.8.21
0.8.20
0.8.19
0.8.18
0.8.17
0.8.16
0.8.15
0.8.14
0.8.13
0.8.12
0.8.11
0.8.1
0.8.0
0.7.24
0.7.23
0.7.22
0.7.21
0.7.20
0.7.19
0.7.18
0.7.17
0.7.16
0.7.15
0.7.14
0.7.13
0.7.12
0.7.11
0.7.10
0.7.9
0.7.8
0.7.7
0.7.6
0.7.5
0.7.3
0.7.2
0.7.1
0.7.0
0.6.9
0.6.8
0.6.7
0.6.6
0.6.5
0.6.4
0.6.3
0.6.1
0.6.0
0.5.9
0.5.8
0.5.7
0.5.6
0.5.5
0.5.4
0.5.3
0.5.2
0.5.1
0.5.0
0.4.44
0.4.43
0.4.42
0.4.41
0.4.40
0.4.39
0.4.38
0.4.37
0.4.36
0.4.35
0.4.34
0.4.33
0.4.32
0.4.30
0.4.29
0.4.28
0.4.27
0.4.26
0.4.25
0.4.24
0.4.23
0.4.22
0.4.21
0.4.20
0.4.19
0.4.18
0.4.17
0.4.16
0.4.15
0.4.14
0.4.13
0.4.12
0.4.11
0.4.10
0.4.9
0.4.8
0.4.7
0.4.6
0.4.5
0.4.4
0.4.3
0.4.2
0.4.1
0.4.0
0.3.0
0.2.0
0.1.0
AI code archaeology
Current section
Files
Jump to
Current section
Files
lib/ai.ex
defmodule AI do
defstruct [:client]
@api_key System.get_env("OPENAI_API_KEY")
@api_timeout 45_000
@embedding_model "text-embedding-3-large"
@summary_model "gpt-4o-mini"
@summary_prompt """
You are a command line program that summarizes the content of a code file,
like an intelligent `ctags`.
Produce the following data from the input file:
- Synopsis
- Languages present in the file
- Business logic and behaviors
- List of symbols
- Map of calls to other modules
Restrict your analysis to only that which appears in this file. This is used
to generate a search index, and we want to avoid false positives from things
like imports.
Respond ONLY with your markdown-formatted summary.
"""
def new() do
openai = OpenaiEx.new(@api_key) |> OpenaiEx.with_receive_timeout(@api_timeout)
%AI{client: openai}
end
def get_embeddings(ai, text) do
embeddings =
split_text(text, 8192)
|> Enum.map(fn chunk ->
OpenaiEx.Embeddings.create(
ai.client,
OpenaiEx.Embeddings.new(
model: @embedding_model,
input: chunk
)
)
|> case do
{:ok, %{"data" => [%{"embedding" => embedding}]}} -> embedding
_ -> nil
end
end)
|> Enum.filter(fn x -> not is_nil(x) end)
{:ok, embeddings}
end
def get_summary(ai, file, text) do
input = "# File name: #{file}\n```\n#{text}\n```"
# The model is limited to 128k tokens input, so, for now, we'll just
# truncate the input if it's too long.
input = truncate_text(input, 128_000)
OpenaiEx.Chat.Completions.create(
ai.client,
OpenaiEx.Chat.Completions.new(
model: @summary_model,
messages: [
OpenaiEx.ChatMessage.system(@summary_prompt),
OpenaiEx.ChatMessage.user(input)
]
)
)
|> case do
{:ok, %{"choices" => [%{"message" => %{"content" => summary}}]}} -> {:ok, summary}
{:error, reason} -> {:error, reason}
response -> {:error, "unexpected response: #{inspect(response)}"}
end
end
defp truncate_text(text, max_tokens) do
if String.length(text) > max_tokens do
String.slice(text, 0, max_tokens)
else
text
end
end
defp split_text(input, max_tokens) do
Gpt3Tokenizer.encode(input)
|> Enum.chunk_every(max_tokens)
|> Enum.map(&Gpt3Tokenizer.decode(&1))
end
end