docs: add unified LLM loader example for OpenAI, Groq, Ollama, OpenRouter

[shravankumar147]

Description:
Added a new tutorial llm_loader.py and llm_loader.ipynb in docs/docs/tutorials/ that demonstrates how to load LLMs from different providers (OpenAI, OpenRouter, Groq, Ollama) with a unified function.

Issue:
N/A (tutorial contribution)

Dependencies:
No new dependencies. Uses existing optional integrations: langchain_openai, langchain_groq, langchain_ollama.

Twitter handle:
@shravankumar147

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
langchain	Ready	Preview	Comment	Aug 20, 2025 5:35pm

[codspeed-hq]

CodSpeed WallTime Performance Report

Merging #32620 will improve performances by 11.7%

_{Comparing shravankumar147:feature/llm-loader (b6b8d6a) with master (f896bcd)}

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

Summary

⚡ 3 improvements
✅ 10 untouched benchmarks

Benchmarks breakdown

	Benchmark	BASE	HEAD	Change
⚡	test_import_time[BaseChatModel]	537.2 ms	480.9 ms	+11.7%
⚡	test_import_time[ChatPromptTemplate]	449.3 ms	406.6 ms	+10.51%
⚡	test_import_time[InMemoryVectorStore]	264.2 ms	236.6 ms	+11.64%

[codspeed-hq]

CodSpeed Instrumentation Performance Report

Merging #32620 will not alter performance

_{Comparing shravankumar147:feature/llm-loader (b6b8d6a) with master (f896bcd)}

Summary

✅ 14 untouched benchmarks

[mdrxy]

Sorry, we are not taking new tutorial submissions at this time. If you would like, you can propose an addition to the new docs repo in a few weeks once things settle down there.

Thank you!