You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
80 lines
2.8 KiB
80 lines
2.8 KiB
import asyncio
|
|
from raganything import RAGAnything
|
|
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
|
|
from lightrag.utils import EmbeddingFunc
|
|
|
|
async def main():
|
|
# Initialize RAGAnything
|
|
rag = RAGAnything(
|
|
working_dir="./rag_storage",
|
|
llm_model_func=lambda prompt, system_prompt=None, history_messages=[], **kwargs: openai_complete_if_cache(
|
|
"gpt-4o-mini",
|
|
prompt,
|
|
system_prompt=system_prompt,
|
|
history_messages=history_messages,
|
|
api_key="your-api-key",
|
|
**kwargs,
|
|
),
|
|
vision_model_func=lambda prompt, system_prompt=None, history_messages=[], image_data=None, **kwargs: openai_complete_if_cache(
|
|
"gpt-4o",
|
|
"",
|
|
system_prompt=None,
|
|
history_messages=[],
|
|
messages=[
|
|
{"role": "system", "content": system_prompt} if system_prompt else None,
|
|
{"role": "user", "content": [
|
|
{"type": "text", "text": prompt},
|
|
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}}
|
|
]} if image_data else {"role": "user", "content": prompt}
|
|
],
|
|
api_key="your-api-key",
|
|
**kwargs,
|
|
) if image_data else openai_complete_if_cache(
|
|
"gpt-4o-mini",
|
|
prompt,
|
|
system_prompt=system_prompt,
|
|
history_messages=history_messages,
|
|
api_key="your-api-key",
|
|
**kwargs,
|
|
),
|
|
embedding_func=EmbeddingFunc(
|
|
embedding_dim=3072,
|
|
max_token_size=8192,
|
|
func=lambda texts: openai_embed(
|
|
texts,
|
|
model="text-embedding-3-large",
|
|
api_key=api_key,
|
|
base_url=base_url,
|
|
),
|
|
),
|
|
)
|
|
|
|
# Process a document
|
|
await rag.process_document_complete(
|
|
file_path="path/to/your/document.pdf",
|
|
output_dir="./output",
|
|
parse_method="auto"
|
|
)
|
|
|
|
# Query the processed content
|
|
# Pure text query - for basic knowledge base search
|
|
text_result = await rag.aquery(
|
|
"What are the main findings shown in the figures and tables?",
|
|
mode="hybrid"
|
|
)
|
|
print("Text query result:", text_result)
|
|
|
|
# Multimodal query with specific multimodal content
|
|
multimodal_result = await rag.aquery_with_multimodal(
|
|
"Explain this formula and its relevance to the document content",
|
|
multimodal_content=[{
|
|
"type": "equation",
|
|
"latex": "P(d|q) = \\frac{P(q|d) \\cdot P(d)}{P(q)}",
|
|
"equation_caption": "Document relevance probability"
|
|
}],
|
|
mode="hybrid"
|
|
)
|
|
print("Multimodal query result:", multimodal_result)
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main()) |