"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?)."
"- Load all community reports in the `community_reports` table from the indexing engine, to be used as context data for global search.\n",
"- Load entities from the `entities` tables from the 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 `communities` table from the indexing engine, to be used to reconstruct the community graph hierarchy for dynamic community selection."
" 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_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",
" \"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",
" 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",
"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"
