Utilities
Prompt an OpenAI model over a workflow file
OpenAI chat responses from a file and a prompt.
Python · Apache-2.0 license
overview
What openai-file does
openai-file is the LLM step in a pipeline: it sends a file and a prompt to an OpenAI chat model and writes the response for the next node.
Model choice is gpt4, 4-32k, chatgpt, or chatgpt-16k. Larger windows fit bigger files at higher cost. The API key arrives as a file input, not on the command line.
Point it at a scan report, findings list, or crawled text when you need summarize, classify, or rewrite before a human or another tool.
source github.com/simonw/llm
use cases
Where openai-file fits
Summarize a scan report
Feed a findings file with a prompt that asks for a short summary, so a long report becomes a few readable lines for the next reviewer.
Classify or triage findings
Pass a list of results and ask the model to group or rank them, turning unsorted output into a prioritized view inside the workflow.
Pick the model for the file size
Choose gpt-4-32k or the 16k turbo variant when the input file is large, or a smaller model when context and cost should stay low.
Rewrite output for a report
Prompt the model to reshape raw tool text into prose for a writeup, keeping the rewrite inside the pipeline rather than a manual step.
reference
openai-file inputs and flags
| Name | Type | Flag | Description |
|---|---|---|---|
| input-file | FILE | · | Input file for the model to read. |
| prompt | STRING | · | Prompt applied to the file input. |
| open-ai-api-key | FILE | · | OpenAI API key, supplied as a file. |
| gpt-4 | BOOLEAN | gpt4 | Use OpenAI Chat gpt-4 (aliases 4, gpt4). |
| gpt-4-32k | BOOLEAN | 4-32k | Use OpenAI Chat gpt-4-32k for larger context. |
| gpt-3-5-turbo | BOOLEAN | chatgpt | Use OpenAI Chat gpt-3.5-turbo (aliases 3.5, chatgpt). |
| gpt-3-5-turbo-16k | BOOLEAN | chatgpt-16k | Use OpenAI Chat gpt-3.5-turbo-16k for a wider context window. |
Showing key inputs. openai-file exposes 7 inputs in total.
example
Run openai-file
# openai-file: summarize hosts.txt with gpt-4
# openai-file input=hosts.txt prompt="List live hosts" gpt4Live hosts from the scan:
api.example.com
app.example.com
staging.example.com
dev.example.com
mail.example.com
vpn.example.com
# openai-file summary of 6 hostsguidance
Choosing openai-file
Use openai-file when a workflow needs an LLM to read a file and return text. It calls OpenAI and needs a key plus outbound access. For deterministic transforms without a model, prefer a text or report utility.
json2html
Renders structured data without a model. Prefer it for deterministic transforms.
generate-yaml-report
Builds reports from fixed templates. openai-file uses an LLM for free-form text.
gron
Flattens JSON for grepping. openai-file is generative summarizing, not mechanical reformatting.
faq
openai-file questions
related
More Utilities tools
browser-fetch
Headless Chromium render: requested URL, final URL, status, and title next to the page.
cewl
Spider a URL and return a wordlist for password crackers.
csvkit
SQL on one CSV. The table name is the file stem.
dnsgen
Wordlist and mined-word subdomain permutation.
duckdb
In-process SQL on CSV, JSON, and Parquet. No server.
edge-tts
Microsoft Edge neural speech from text or a script file. No API key.
Run openai-file yourself
A scan report and an API key feed openai-file, which prompts an OpenAI model over the file and writes the generated summary as output.
Facts on this page come from the live Trickest tool library.