How to Perform Metadata Extraction and Tagging with Other LLMs (e.g., Claude and Gemini) Instead of OpenAI Metadata Tagger

[myaeisan77]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

schema = {
    "properties": {
        "movie_title": {"type": "string"},
        "critic": {"type": "string"},
        "tone": {"type": "string", "enum": ["positive", "negative"]},
        "rating": {
            "type": "integer",
            "description": "The number of stars the critic rated the movie",
        },
    },
    "required": ["movie_title", "critic", "tone"],
}

# Must be an OpenAI model that supports functions
llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
document_transformer = create_metadata_tagger(metadata_schema=schema, llm=llm)

Description

I am doing metadata extraction and tagging of PDF files using the OpenAI metadata tagger supported by LangChain. I would like to use other LLMs (such as Gemini, Claude) in addition to OpenAI models.

1.Could you please tell me the tagging function for use with other LLMs?
2. What are some good alternative methods for implementing metadata extraction and tagging?

System Info

System Information

OS: Linux
OS Version: #220-Ubuntu SMP Fri Sep 27 13:19:16 UTC 2024
Python Version: 3.10.8 (main, Nov 4 2022, 13:48:29) [GCC 11.2.0]

Package Information

langchain_core: 0.3.22
langchain: 0.3.0
langchain_community: 0.3.7
langchain_anthropic: 0.3.0
langchain_chroma: 0.1.4
langchain_cohere: 0.3.2
langchain_experimental: 0.3.3
langchain_openai: 0.2.9
langchain_text_splitters: 0.3.0