openai_chat_request

Sends a request to a standard OpenAI-compatible endpoint (e.g. /v1/chat/completions).
Used for both OpenAI's official API and local LLMs (Ollama, LM Studio, vLLM).

internal

A pipeline for matching messy company name strings against a clean dictionary (e.g., 'Orbis').
Implements a cascading strategy: Exact -> Fuzzy ('zoomerjoin') -> 'FTS5' ('SQLite') -> Rarity Weighted.
References: Beniamino Green (2025) <https://beniamino.org/zoomerjoin/>; <https://www.sqlite.org/fts5.html>.

Giulian Etingin-Frati

firmmatchr

Robust Probabilistic Matching for German Company Names

openai_chat_request function

<dl><dt>system_msg</dt>
<dd>String. The instructions for the LLM.</dd>
<dt>user_msg</dt>
<dd>String. The specific case to evaluate.</dd>
<dt>endpoint</dt>
<dd>String. Base URL (e.g., "http://localhost:11434/v1").</dd>
<dt>api_key</dt>
<dd>String. API Key. Often not required for local LLMs.</dd>
<dt>model</dt>
<dd>String. Model name.</dd></dl>

Arguments

Internal OpenAI/Local LLM Chat Completion Wrapper — openai_chat_request

<dl>

<dt>system_msg</dt>
<dd>String. The instructions for the LLM.</dd>


<dt>user_msg</dt>
<dd>String. The specific case to evaluate.</dd>


<dt>endpoint</dt>
<dd>String. Base URL (e.g., "http://localhost:11434/v1").</dd>


<dt>api_key</dt>
<dd>String. API Key. Often not required for local LLMs.</dd>


<dt>model</dt>
<dd>String. Model name.</dd>

</dl>

openai_chat_request: Internal OpenAI/Local LLM Chat Completion Wrapper

Description

Usage

Value

Arguments