Skip to main content
Version: v1.6.1 🚧

View a document summary

Overview​

Users can access a document summary.

Example​

from h2ogpte import H2OGPTE

client = H2OGPTE(
    address="https://h2ogpte.genai.h2o.ai",
    api_key='sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX',
)

list_of_documents_with_summaries = client.list_recent_documents_with_summaries(offset=0, limit=1)

document = list_of_documents_with_summaries[0]

print(
    f"Connector: {document.connector}\n"
    f"Guardrails settings: {document.guardrails_settings}\n"
    f"ID: {document.id}\n"
    f"Metadata: {document.meta_data_dict}\n"
    f"Model computed fields: {document.model_computed_fields}\n"
    f"Model config: {document.model_config}\n"
    f"Model fields: {document.model_fields}\n"
    f"Name: {document.name}\n"
    f"Original type: {document.original_type}\n"
    f"Page count: {document.page_count}\n"
    f"Size: {document.size}\n"
    f"Status: {document.status}\n"
    f"Summary: {document.summary}\n"
    f"Summary parameters: {document.summary_parameters}\n"
    f"Type: {document.type}\n"
    f"Updated at: {document.updated_at}\n"
    f"URI: {document.uri}\n"
    f"Usage stats: {document.usage_stats}\n"
    f"Username: {document.username}"
)
Connector: Upload
Guardrails settings: None
ID: e5d4b814-9377-4df8-a664-400dd9c577ae
Metadata: {}
Model computed fields: {}
Model config: {'use_enum_values': True}
Model fields: {'id': FieldInfo(annotation=str, required=True), 'username': FieldInfo(annotation=str, required=True), 'name': FieldInfo(annotation=str, required=True), 'type': FieldInfo(annotation=str, required=True), 'size': FieldInfo(annotation=int, required=True), 'page_count': FieldInfo(annotation=int, required=True), 'guardrails_settings': FieldInfo(annotation=Union[dict, NoneType], required=False, default=None), 'connector': FieldInfo(annotation=Union[str, NoneType], required=False, default=None), 'uri': FieldInfo(annotation=Union[str, NoneType], required=False, default=None), 'original_type': FieldInfo(annotation=Union[str, NoneType], required=False, default=None), 'meta_data_dict': FieldInfo(annotation=Union[dict, NoneType], required=False, default=None), 'status': FieldInfo(annotation=Status, required=True), 'updated_at': FieldInfo(annotation=datetime, required=True), 'usage_stats': FieldInfo(annotation=Union[str, NoneType], required=True), 'summary': FieldInfo(annotation=Union[str, NoneType], required=True), 'summary_parameters': FieldInfo(annotation=Union[str, NoneType], required=True)}
Name: annual-report.pdf
Original type: PDF
Page count: 226
Size: 3590271
Status: completed
Summary: Wells Fargo's 2021 Annual Report highlights strong financial performance with a 12.0% return on equity and a 14.3% return on tangible common equity. The company saw a 6% increase in revenue, driven by gains in affiliated venture capital and private equity businesses, and the sale of certain businesses. Despite the challenges posed by the COVID-19 pandemic, Wells Fargo returned $16.9 billion to shareholders through dividends and stock repurchases. The company's strong foundation, focused business, and cultural changes position it for long-term success.
Summary parameters: {"system_prompt": "You are h2oGPTe, an expert question-answering AI system created by H2O.ai.", "pre_prompt_summary": "In order to write a concise single-paragraph or bulleted list summary, pay attention to any chat history, any images given, or any following text:", "prompt_summary": "Using only any chat history, any images given, or any text above, write a condensed and concise well-structured Markdown summary of key results.", "llm": "h2oai/h2o-danube3-4b-chat", "llm_args": {}, "max_num_chunks": 25, "sampling_strategy": "auto", "keep_intermediate_results": false, "guided_json": null, "pages": null, "guardrails_settings": {}, "image_batch_image_prompt": "<response_instructions>\n- Act as a keen observer with a sharp eye for detail.\n- Analyze the content within the images.\n- Provide insights based on your observations.\n- Avoid making up facts.\n- Do not forget to follow the system prompt.\n</response_instructions>\n", "image_batch_final_prompt": "<response_instructions>\n- Check if the answers already given in <image> XML tags are useful.\n  - Image answers came from a vision model capable of reading text and images within the images.\n  - If image answers are useful, preserve all details the image answers provide and use them to construct a well-structured answer.\n- Ignore image answers that had no useful content, because any single batch of images may not be relevant. Focus on all details from image answers that are relevant and useful.\n- Check if the document text can answer the question.\n- Check if the chat history can answer the question.\n- Check if any figure captions can answer the question.\n- If answers conflict between text, chat history, and figure captions, do not focus your response on this conflict.\n  - In handling conflicting answers, use logical reasoning and supporting evidence to assess the plausibility of each answer.\n  - In handling conflicting answers, choose the most consistent answer -- i.e., the most common answer among conflicts (self-consistency reasoning) or one that aligns with well-established facts.\n  - In handling conflicting answers, one may choose one data source over another -- i.e., text is probably more reliable than an image when the question can be answered from text, while an image is more reliable than text for flowcharts, photos, etc.\n- Do not forget to follow the system prompt.\n- Finally, according to our chat history, the above documents, figure captions, or given images, construct a well-structured response.\n</response_instructions>\n"}
Type: PDF
Updated at: 2024-10-31 20:06:00.129495+00:00
URI: None
Usage stats: {"response_time": "4.2060 seconds", "cost": "0.00124 [USD]", "llm_args": {}, "num_chunks": 25, "num_images": 0, "usage": [{"llm": "h2oai/h2o-danube3-4b-chat", "input_tokens": 12104, "output_tokens": 113, "tokens_per_second": 34.412, "time_to_first_token": 1.1155519485473633, "origin": "process_document", "cost": "0.00124 [USD]"}]}
Username: sergio.perez@h2o.ai
Feedback