mirror of
https://github.com/microsoft/graphrag.git
synced 2025-06-26 23:19:58 +00:00
e53422366d
* update gitignore * add dynamic community sleection to updated main branch * update SearchResult to record output_tokens. * update search result * dynamic search working * format * add llm_calls_categories and prompt_tokens and output_tokens cate * update * formatting * log drift search output and prompt tokens separately * update global_search.ipynb. update operate dulce dataset and add create_final_communities. update dynamic community selection init * add .ipynb back to cspell.config.yaml * format * add notebook example on dynamic search * rearrange * update gitignore * format code * code format * code format * fix default variable --------- Co-authored-by: Bryan Li <bryanlimy@gmail.com>
616 lines
26 KiB
Plaintext
616 lines
26 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Copyright (c) 2024 Microsoft Corporation.\n",
|
|
"# Licensed under the MIT License."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"\n",
|
|
"import pandas as pd\n",
|
|
"import tiktoken\n",
|
|
"\n",
|
|
"from graphrag.query.indexer_adapters import (\n",
|
|
" read_indexer_communities,\n",
|
|
" read_indexer_entities,\n",
|
|
" read_indexer_reports,\n",
|
|
")\n",
|
|
"from graphrag.query.llm.oai.chat_openai import ChatOpenAI\n",
|
|
"from graphrag.query.llm.oai.typing import OpenaiApiType\n",
|
|
"from graphrag.query.structured_search.global_search.community_context import (\n",
|
|
" GlobalCommunityContext,\n",
|
|
")\n",
|
|
"from graphrag.query.structured_search.global_search.search import GlobalSearch"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Global Search example\n",
|
|
"\n",
|
|
"Global search method generates answers by searching over all AI-generated community reports in a map-reduce fashion. This is a resource-intensive method, but often gives good responses for questions that require an understanding of the dataset as a whole (e.g. What are the most significant values of the herbs mentioned in this notebook?)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### LLM setup"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"api_key = os.environ[\"GRAPHRAG_API_KEY\"]\n",
|
|
"llm_model = os.environ[\"GRAPHRAG_LLM_MODEL\"]\n",
|
|
"\n",
|
|
"llm = ChatOpenAI(\n",
|
|
" api_key=api_key,\n",
|
|
" model=llm_model,\n",
|
|
" api_type=OpenaiApiType.OpenAI, # OpenaiApiType.OpenAI or OpenaiApiType.AzureOpenAI\n",
|
|
" max_retries=20,\n",
|
|
")\n",
|
|
"\n",
|
|
"token_encoder = tiktoken.encoding_for_model(llm_model)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Load community reports as context for global search\n",
|
|
"\n",
|
|
"- Load all community reports in the `create_final_community_reports` table from the ire-indexing engine, to be used as context data for global search.\n",
|
|
"- Load entities from the `create_final_nodes` and `create_final_entities` tables from the ire-indexing engine, to be used for calculating community weights for context ranking. Note that this is optional (if no entities are provided, we will not calculate community weights and only use the rank attribute in the community reports table for context ranking)\n",
|
|
"- Load all communities in the `create_final_communites` table from the ire-indexing engine, to be used to reconstruct the community graph hierarchy for dynamic community selection."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# parquet files generated from indexing pipeline\n",
|
|
"INPUT_DIR = \"./inputs/operation dulce\"\n",
|
|
"COMMUNITY_TABLE = \"create_final_communities\"\n",
|
|
"COMMUNITY_REPORT_TABLE = \"create_final_community_reports\"\n",
|
|
"ENTITY_TABLE = \"create_final_nodes\"\n",
|
|
"ENTITY_EMBEDDING_TABLE = \"create_final_entities\"\n",
|
|
"\n",
|
|
"# we don't fix a specific community level but instead use an agent to dynamicially\n",
|
|
"# search through all the community reports to check if they are relevant.\n",
|
|
"COMMUNITY_LEVEL = None"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Total report count: 20\n",
|
|
"Report count after filtering by community level None: 20\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>community</th>\n",
|
|
" <th>full_content</th>\n",
|
|
" <th>level</th>\n",
|
|
" <th>rank</th>\n",
|
|
" <th>title</th>\n",
|
|
" <th>rank_explanation</th>\n",
|
|
" <th>summary</th>\n",
|
|
" <th>findings</th>\n",
|
|
" <th>full_content_json</th>\n",
|
|
" <th>id</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>10</td>\n",
|
|
" <td># Paranormal Military Squad at Dulce Base: Dec...</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" <td>Paranormal Military Squad at Dulce Base: Decod...</td>\n",
|
|
" <td>The impact severity rating is high due to the ...</td>\n",
|
|
" <td>The Paranormal Military Squad, stationed at Du...</td>\n",
|
|
" <td>[{'explanation': 'Jordan is a central figure i...</td>\n",
|
|
" <td>{\\n \"title\": \"Paranormal Military Squad at ...</td>\n",
|
|
" <td>1ba2d200-dd26-4693-affe-a5539d0a0e0d</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>11</td>\n",
|
|
" <td># Dulce and Paranormal Military Squad Operatio...</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" <td>Dulce and Paranormal Military Squad Operations</td>\n",
|
|
" <td>The impact severity rating is high due to the ...</td>\n",
|
|
" <td>The community centers around Dulce, a secretiv...</td>\n",
|
|
" <td>[{'explanation': 'Dulce is described as a top-...</td>\n",
|
|
" <td>{\\n \"title\": \"Dulce and Paranormal Military...</td>\n",
|
|
" <td>a8a530b0-ae6b-44ea-b11c-9f70d138298d</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>12</td>\n",
|
|
" <td># Paranormal Military Squad and Dulce Base Ope...</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>7.5</td>\n",
|
|
" <td>Paranormal Military Squad and Dulce Base Opera...</td>\n",
|
|
" <td>The impact severity rating is relatively high ...</td>\n",
|
|
" <td>The community centers around the Paranormal Mi...</td>\n",
|
|
" <td>[{'explanation': 'Taylor is a central figure w...</td>\n",
|
|
" <td>{\\n \"title\": \"Paranormal Military Squad and...</td>\n",
|
|
" <td>0478975b-c805-4cc1-b746-82f3e689e2f3</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>13</td>\n",
|
|
" <td># Mission Dynamics and Leadership: Cruz and Wa...</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>7.5</td>\n",
|
|
" <td>Mission Dynamics and Leadership: Cruz and Wash...</td>\n",
|
|
" <td>The impact severity rating is relatively high ...</td>\n",
|
|
" <td>This report explores the intricate dynamics of...</td>\n",
|
|
" <td>[{'explanation': 'Cruz is a central figure in ...</td>\n",
|
|
" <td>{\\n \"title\": \"Mission Dynamics and Leadersh...</td>\n",
|
|
" <td>b56f6e68-3951-4f07-8760-63700944a375</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>14</td>\n",
|
|
" <td># Dulce Base and Paranormal Military Squad: Br...</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" <td>Dulce Base and Paranormal Military Squad: Brid...</td>\n",
|
|
" <td>The impact severity rating is high due to the ...</td>\n",
|
|
" <td>The community centers around the Dulce Base, a...</td>\n",
|
|
" <td>[{'explanation': 'Sam Rivera, a member of the ...</td>\n",
|
|
" <td>{\\n \"title\": \"Dulce Base and Paranormal Mil...</td>\n",
|
|
" <td>736e7006-d050-4abb-a122-00febf3f540f</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" community full_content level rank \\\n",
|
|
"0 10 # Paranormal Military Squad at Dulce Base: Dec... 1 8.5 \n",
|
|
"1 11 # Dulce and Paranormal Military Squad Operatio... 1 8.5 \n",
|
|
"2 12 # Paranormal Military Squad and Dulce Base Ope... 1 7.5 \n",
|
|
"3 13 # Mission Dynamics and Leadership: Cruz and Wa... 1 7.5 \n",
|
|
"4 14 # Dulce Base and Paranormal Military Squad: Br... 1 8.5 \n",
|
|
"\n",
|
|
" title \\\n",
|
|
"0 Paranormal Military Squad at Dulce Base: Decod... \n",
|
|
"1 Dulce and Paranormal Military Squad Operations \n",
|
|
"2 Paranormal Military Squad and Dulce Base Opera... \n",
|
|
"3 Mission Dynamics and Leadership: Cruz and Wash... \n",
|
|
"4 Dulce Base and Paranormal Military Squad: Brid... \n",
|
|
"\n",
|
|
" rank_explanation \\\n",
|
|
"0 The impact severity rating is high due to the ... \n",
|
|
"1 The impact severity rating is high due to the ... \n",
|
|
"2 The impact severity rating is relatively high ... \n",
|
|
"3 The impact severity rating is relatively high ... \n",
|
|
"4 The impact severity rating is high due to the ... \n",
|
|
"\n",
|
|
" summary \\\n",
|
|
"0 The Paranormal Military Squad, stationed at Du... \n",
|
|
"1 The community centers around Dulce, a secretiv... \n",
|
|
"2 The community centers around the Paranormal Mi... \n",
|
|
"3 This report explores the intricate dynamics of... \n",
|
|
"4 The community centers around the Dulce Base, a... \n",
|
|
"\n",
|
|
" findings \\\n",
|
|
"0 [{'explanation': 'Jordan is a central figure i... \n",
|
|
"1 [{'explanation': 'Dulce is described as a top-... \n",
|
|
"2 [{'explanation': 'Taylor is a central figure w... \n",
|
|
"3 [{'explanation': 'Cruz is a central figure in ... \n",
|
|
"4 [{'explanation': 'Sam Rivera, a member of the ... \n",
|
|
"\n",
|
|
" full_content_json \\\n",
|
|
"0 {\\n \"title\": \"Paranormal Military Squad at ... \n",
|
|
"1 {\\n \"title\": \"Dulce and Paranormal Military... \n",
|
|
"2 {\\n \"title\": \"Paranormal Military Squad and... \n",
|
|
"3 {\\n \"title\": \"Mission Dynamics and Leadersh... \n",
|
|
"4 {\\n \"title\": \"Dulce Base and Paranormal Mil... \n",
|
|
"\n",
|
|
" id \n",
|
|
"0 1ba2d200-dd26-4693-affe-a5539d0a0e0d \n",
|
|
"1 a8a530b0-ae6b-44ea-b11c-9f70d138298d \n",
|
|
"2 0478975b-c805-4cc1-b746-82f3e689e2f3 \n",
|
|
"3 b56f6e68-3951-4f07-8760-63700944a375 \n",
|
|
"4 736e7006-d050-4abb-a122-00febf3f540f "
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"community_df = pd.read_parquet(f\"{INPUT_DIR}/{COMMUNITY_TABLE}.parquet\")\n",
|
|
"entity_df = pd.read_parquet(f\"{INPUT_DIR}/{ENTITY_TABLE}.parquet\")\n",
|
|
"report_df = pd.read_parquet(f\"{INPUT_DIR}/{COMMUNITY_REPORT_TABLE}.parquet\")\n",
|
|
"entity_embedding_df = pd.read_parquet(f\"{INPUT_DIR}/{ENTITY_EMBEDDING_TABLE}.parquet\")\n",
|
|
"\n",
|
|
"communities = read_indexer_communities(community_df, entity_df, report_df)\n",
|
|
"reports = read_indexer_reports(\n",
|
|
" report_df,\n",
|
|
" entity_df,\n",
|
|
" community_level=COMMUNITY_LEVEL,\n",
|
|
" dynamic_community_selection=True,\n",
|
|
")\n",
|
|
"entities = read_indexer_entities(\n",
|
|
" entity_df, entity_embedding_df, community_level=COMMUNITY_LEVEL\n",
|
|
")\n",
|
|
"\n",
|
|
"print(f\"Total report count: {len(report_df)}\")\n",
|
|
"print(\n",
|
|
" f\"Report count after filtering by community level {COMMUNITY_LEVEL}: {len(reports)}\"\n",
|
|
")\n",
|
|
"\n",
|
|
"report_df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"#### Build global context with dynamic community selection\n",
|
|
"\n",
|
|
"The goal of dynamic community selection reduce the number of community reports that need to be processed in the map-reduce operation. To that end, we take advantage of the hierachical structure of the indexed dataset. We first ask the LLM to rate how relevant each level 0 community is with respect to the user query, we then traverse down the child node(s) if the current community report is deemed relevant.\n",
|
|
"\n",
|
|
"You can still set a `COMMUNITY_LEVEL` to filter out lower level community reports and apply dynamic community selection on the filtered reports.\n",
|
|
"\n",
|
|
"Note that the dataset is quite small, with only consist of 20 communities from 2 levels (level 0 and 1). Dynamic community selection is more effective when there are large amount of content to be filtered out."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"mini_llm = ChatOpenAI(\n",
|
|
" api_key=api_key,\n",
|
|
" model=\"gpt-4o-mini\",\n",
|
|
" api_type=OpenaiApiType.OpenAI, # OpenaiApiType.OpenAI or OpenaiApiType.AzureOpenAI\n",
|
|
" max_retries=20,\n",
|
|
")\n",
|
|
"mini_token_encoder = tiktoken.encoding_for_model(mini_llm.model)\n",
|
|
"\n",
|
|
"context_builder = GlobalCommunityContext(\n",
|
|
" community_reports=reports,\n",
|
|
" communities=communities,\n",
|
|
" entities=entities, # default to None if you don't want to use community weights for ranking\n",
|
|
" token_encoder=token_encoder,\n",
|
|
" dynamic_community_selection=True,\n",
|
|
" dynamic_community_selection_kwargs={\n",
|
|
" \"llm\": mini_llm,\n",
|
|
" \"token_encoder\": mini_token_encoder,\n",
|
|
" },\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"#### Perform global search with dynamic community selection"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"context_builder_params = {\n",
|
|
" \"use_community_summary\": False, # False means using full community reports. True means using community short summaries.\n",
|
|
" \"shuffle_data\": True,\n",
|
|
" \"include_community_rank\": True,\n",
|
|
" \"min_community_rank\": 0,\n",
|
|
" \"community_rank_name\": \"rank\",\n",
|
|
" \"include_community_weight\": True,\n",
|
|
" \"community_weight_name\": \"occurrence weight\",\n",
|
|
" \"normalize_community_weight\": True,\n",
|
|
" \"max_tokens\": 12_000, # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)\n",
|
|
" \"context_name\": \"Reports\",\n",
|
|
"}\n",
|
|
"\n",
|
|
"map_llm_params = {\n",
|
|
" \"max_tokens\": 1000,\n",
|
|
" \"temperature\": 0.0,\n",
|
|
" \"response_format\": {\"type\": \"json_object\"},\n",
|
|
"}\n",
|
|
"\n",
|
|
"reduce_llm_params = {\n",
|
|
" \"max_tokens\": 2000, # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 1000-1500)\n",
|
|
" \"temperature\": 0.0,\n",
|
|
"}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"search_engine = GlobalSearch(\n",
|
|
" llm=llm,\n",
|
|
" context_builder=context_builder,\n",
|
|
" token_encoder=token_encoder,\n",
|
|
" max_data_tokens=12_000, # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)\n",
|
|
" map_llm_params=map_llm_params,\n",
|
|
" reduce_llm_params=reduce_llm_params,\n",
|
|
" allow_general_knowledge=False, # set this to True will add instruction to encourage the LLM to incorporate general knowledge in the response, which may increase hallucinations, but could be useful in some use cases.\n",
|
|
" json_mode=True, # set this to False if your LLM model does not support JSON mode.\n",
|
|
" context_builder_params=context_builder_params,\n",
|
|
" concurrent_coroutines=32,\n",
|
|
" response_type=\"multiple paragraphs\", # free form text describing the response type and format, can be anything, e.g. prioritized list, single paragraph, multiple paragraphs, multiple-page report\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"### Overview of Cosmic Vocalization\n",
|
|
"\n",
|
|
"Cosmic Vocalization is a phenomenon that has captured the attention of various individuals and groups, becoming a focal point for community interest. It is perceived as a significant cosmic event, with interpretations ranging from a strategic security concern to a metaphorical interstellar duet [Data: Reports (6)].\n",
|
|
"\n",
|
|
"### Key Stakeholders and Perspectives\n",
|
|
"\n",
|
|
"1. **Paranormal Military Squad**: This group is actively engaged with Cosmic Vocalization, treating it as a strategic element in their security measures. Their involvement underscores the importance of Cosmic Vocalization in broader security contexts. They metaphorically view the Universe as a concert hall, suggesting a unique perspective on cosmic events and their implications for human entities [Data: Reports (6)].\n",
|
|
"\n",
|
|
"2. **Alex Mercer**: Alex Mercer perceives Cosmic Vocalization as part of an interstellar duet, indicating a responsive and perhaps artistic approach to understanding these cosmic phenomena. This perspective highlights the diverse interpretations and cultural significance attributed to Cosmic Vocalization [Data: Reports (6)].\n",
|
|
"\n",
|
|
"3. **Taylor Cruz**: Taylor Cruz expresses concerns about Cosmic Vocalization, fearing it might serve as a homing tune. This perspective introduces a layer of urgency and potential threat, suggesting that Cosmic Vocalization could have implications beyond mere observation, possibly affecting security or existential considerations [Data: Reports (6)].\n",
|
|
"\n",
|
|
"### Implications\n",
|
|
"\n",
|
|
"The involvement of these stakeholders and their varied perspectives on Cosmic Vocalization illustrate the complexity and multifaceted nature of this phenomenon. It is not only a subject of scientific and strategic interest but also a cultural and existential topic that prompts diverse interpretations and responses. The strategic engagement by the Paranormal Military Squad and the concerns raised by individuals like Taylor Cruz highlight the potential significance of Cosmic Vocalization in both security and broader cosmic contexts [Data: Reports (6)].\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"result = await search_engine.asearch(\n",
|
|
" \"What is Cosmic Vocalization and who are involved in it?\"\n",
|
|
")\n",
|
|
"\n",
|
|
"print(result.response)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>id</th>\n",
|
|
" <th>title</th>\n",
|
|
" <th>occurrence weight</th>\n",
|
|
" <th>content</th>\n",
|
|
" <th>rank</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>15</td>\n",
|
|
" <td>Dulce Base and the Paranormal Military Squad: ...</td>\n",
|
|
" <td>1.00</td>\n",
|
|
" <td># Dulce Base and the Paranormal Military Squad...</td>\n",
|
|
" <td>9.5</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>1</td>\n",
|
|
" <td>Earth's Interstellar Communication Initiative</td>\n",
|
|
" <td>0.16</td>\n",
|
|
" <td># Earth's Interstellar Communication Initiativ...</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>16</td>\n",
|
|
" <td>Dulce Military Base and Alien Intelligence Com...</td>\n",
|
|
" <td>0.08</td>\n",
|
|
" <td># Dulce Military Base and Alien Intelligence C...</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>18</td>\n",
|
|
" <td>Paranormal Military Squad Team and Dulce Base'...</td>\n",
|
|
" <td>0.04</td>\n",
|
|
" <td># Paranormal Military Squad Team and Dulce Bas...</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>19</td>\n",
|
|
" <td>Central Terminal and Viewing Monitors at Dulce...</td>\n",
|
|
" <td>0.02</td>\n",
|
|
" <td># Central Terminal and Viewing Monitors at Dul...</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>5</th>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Dulce Facility and Control Room of Dulce: Extr...</td>\n",
|
|
" <td>0.02</td>\n",
|
|
" <td># Dulce Facility and Control Room of Dulce: Ex...</td>\n",
|
|
" <td>8.5</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>6</th>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Cosmic Vocalization and Universe Interactions</td>\n",
|
|
" <td>0.02</td>\n",
|
|
" <td># Cosmic Vocalization and Universe Interaction...</td>\n",
|
|
" <td>7.5</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" id title occurrence weight \\\n",
|
|
"0 15 Dulce Base and the Paranormal Military Squad: ... 1.00 \n",
|
|
"1 1 Earth's Interstellar Communication Initiative 0.16 \n",
|
|
"2 16 Dulce Military Base and Alien Intelligence Com... 0.08 \n",
|
|
"3 18 Paranormal Military Squad Team and Dulce Base'... 0.04 \n",
|
|
"4 19 Central Terminal and Viewing Monitors at Dulce... 0.02 \n",
|
|
"5 4 Dulce Facility and Control Room of Dulce: Extr... 0.02 \n",
|
|
"6 6 Cosmic Vocalization and Universe Interactions 0.02 \n",
|
|
"\n",
|
|
" content rank \n",
|
|
"0 # Dulce Base and the Paranormal Military Squad... 9.5 \n",
|
|
"1 # Earth's Interstellar Communication Initiativ... 8.5 \n",
|
|
"2 # Dulce Military Base and Alien Intelligence C... 8.5 \n",
|
|
"3 # Paranormal Military Squad Team and Dulce Bas... 8.5 \n",
|
|
"4 # Central Terminal and Viewing Monitors at Dul... 8.5 \n",
|
|
"5 # Dulce Facility and Control Room of Dulce: Ex... 8.5 \n",
|
|
"6 # Cosmic Vocalization and Universe Interaction... 7.5 "
|
|
]
|
|
},
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# inspect the data used to build the context for the LLM responses\n",
|
|
"result.context_data[\"reports\"]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Build context (gpt-4o-mini)\n",
|
|
"LLM calls: 12. Prompt tokens: 8565. Output tokens: 1091.\n",
|
|
"Map-reduce (gpt-4o)\n",
|
|
"LLM calls: 2. Prompt tokens: 5771. Output tokens: 600.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# inspect number of LLM calls and tokens in dynamic community selection\n",
|
|
"llm_calls = result.llm_calls_categories[\"build_context\"]\n",
|
|
"prompt_tokens = result.prompt_tokens_categories[\"build_context\"]\n",
|
|
"output_tokens = result.output_tokens_categories[\"build_context\"]\n",
|
|
"print(\n",
|
|
" f\"Build context ({mini_llm.model})\\nLLM calls: {llm_calls}. Prompt tokens: {prompt_tokens}. Output tokens: {output_tokens}.\"\n",
|
|
")\n",
|
|
"# inspect number of LLM calls and tokens in map-reduce\n",
|
|
"llm_calls = result.llm_calls_categories[\"map\"] + result.llm_calls_categories[\"reduce\"]\n",
|
|
"prompt_tokens = (\n",
|
|
" result.prompt_tokens_categories[\"map\"] + result.prompt_tokens_categories[\"reduce\"]\n",
|
|
")\n",
|
|
"output_tokens = (\n",
|
|
" result.output_tokens_categories[\"map\"] + result.output_tokens_categories[\"reduce\"]\n",
|
|
")\n",
|
|
"print(\n",
|
|
" f\"Map-reduce ({llm.model})\\nLLM calls: {llm_calls}. Prompt tokens: {prompt_tokens}. Output tokens: {output_tokens}.\"\n",
|
|
")"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "graphrag",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.12.5"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|