mirror of
https://github.com/meilisearch/MeiliSearch
synced 2025-07-04 20:37:15 +02:00
Merge 08e096c985
into fef089c7b6
This commit is contained in:
commit
4d12fb43c6
5 changed files with 112 additions and 22 deletions
|
@ -27,9 +27,10 @@ use meilisearch_types::features::{
|
|||
ChatCompletionPrompts as DbChatCompletionPrompts,
|
||||
ChatCompletionSource as DbChatCompletionSource, SystemRole,
|
||||
};
|
||||
use meilisearch_types::heed::RoTxn;
|
||||
use meilisearch_types::keys::actions;
|
||||
use meilisearch_types::milli::index::ChatConfig;
|
||||
use meilisearch_types::milli::{all_obkv_to_json, obkv_to_json, TimeBudget};
|
||||
use meilisearch_types::milli::{all_obkv_to_json, obkv_to_json, OrderBy, TimeBudget};
|
||||
use meilisearch_types::{Document, Index};
|
||||
use serde::Deserialize;
|
||||
use serde_json::json;
|
||||
|
@ -165,6 +166,7 @@ fn setup_search_tool(
|
|||
|
||||
let mut index_uids = Vec::new();
|
||||
let mut function_description = prompts.search_description.clone();
|
||||
let mut filter_description = prompts.search_filter_param.clone();
|
||||
index_scheduler.try_for_each_index::<_, ()>(|name, index| {
|
||||
// Make sure to skip unauthorized indexes
|
||||
if !filters.is_index_authorized(name) {
|
||||
|
@ -176,16 +178,22 @@ fn setup_search_tool(
|
|||
let index_description = chat_config.description;
|
||||
let _ = writeln!(&mut function_description, "\n\n - {name}: {index_description}\n");
|
||||
index_uids.push(name.to_string());
|
||||
let facet_distributions = format_facet_distributions(&index, &rtxn, 10).unwrap(); // TODO do not unwrap
|
||||
let _ = writeln!(&mut filter_description, "\n## Facet distributions of the {name} index");
|
||||
let _ = writeln!(&mut filter_description, "{facet_distributions}");
|
||||
|
||||
Ok(())
|
||||
})?;
|
||||
|
||||
tracing::debug!("LLM function description: {function_description}");
|
||||
tracing::debug!("LLM filter description: {filter_description}");
|
||||
|
||||
let tool = ChatCompletionToolArgs::default()
|
||||
.r#type(ChatCompletionToolType::Function)
|
||||
.function(
|
||||
FunctionObjectArgs::default()
|
||||
.name(MEILI_SEARCH_IN_INDEX_FUNCTION_NAME)
|
||||
.description(&function_description)
|
||||
.description(function_description)
|
||||
.parameters(json!({
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
@ -199,9 +207,13 @@ fn setup_search_tool(
|
|||
// "type": ["string", "null"],
|
||||
"type": "string",
|
||||
"description": prompts.search_q_param,
|
||||
},
|
||||
"filter": {
|
||||
"type": "string",
|
||||
"description": filter_description,
|
||||
}
|
||||
},
|
||||
"required": ["index_uid", "q"],
|
||||
"required": ["index_uid", "q", "filter"],
|
||||
"additionalProperties": false,
|
||||
}))
|
||||
.strict(true)
|
||||
|
@ -243,11 +255,19 @@ async fn process_search_request(
|
|||
auth_token: &str,
|
||||
index_uid: String,
|
||||
q: Option<String>,
|
||||
filter: Option<String>,
|
||||
) -> Result<(Index, Vec<Document>, String), ResponseError> {
|
||||
let index = index_scheduler.index(&index_uid)?;
|
||||
let rtxn = index.static_read_txn()?;
|
||||
let ChatConfig { description: _, prompt: _, search_parameters } = index.chat_config(&rtxn)?;
|
||||
let mut query = SearchQuery { q, ..SearchQuery::from(search_parameters) };
|
||||
let mut query = SearchQuery {
|
||||
q,
|
||||
filter: filter.map(serde_json::Value::from),
|
||||
..SearchQuery::from(search_parameters)
|
||||
};
|
||||
|
||||
tracing::debug!("LLM query: {:?}", query);
|
||||
|
||||
let auth_filter = ActionPolicy::<{ actions::SEARCH }>::authenticate(
|
||||
auth_ctrl,
|
||||
auth_token,
|
||||
|
@ -276,14 +296,23 @@ async fn process_search_request(
|
|||
let (search, _is_finite_pagination, _max_total_hits, _offset) =
|
||||
prepare_search(&index_cloned, &rtxn, &query, &search_kind, time_budget, features)?;
|
||||
|
||||
search_from_kind(index_uid, search_kind, search)
|
||||
.map(|(search_results, _)| (rtxn, search_results))
|
||||
.map_err(ResponseError::from)
|
||||
match search_from_kind(index_uid, search_kind, search) {
|
||||
Ok((search_results, _)) => Ok((rtxn, Ok(search_results))),
|
||||
Err(MeilisearchHttpError::Milli {
|
||||
error: meilisearch_types::milli::Error::UserError(user_error),
|
||||
index_name: _,
|
||||
}) => Ok((rtxn, Err(user_error))),
|
||||
Err(err) => Err(ResponseError::from(err)),
|
||||
}
|
||||
})
|
||||
.await;
|
||||
permit.drop().await;
|
||||
|
||||
let output = output?;
|
||||
let output = match output? {
|
||||
Ok((rtxn, Ok(search_results))) => Ok((rtxn, search_results)),
|
||||
Ok((_rtxn, Err(error))) => return Ok((index, Vec::new(), error.to_string())),
|
||||
Err(err) => Err(ResponseError::from(err)),
|
||||
};
|
||||
let mut documents = Vec::new();
|
||||
if let Ok((ref rtxn, ref search_result)) = output {
|
||||
// aggregate.succeed(search_result);
|
||||
|
@ -391,16 +420,19 @@ async fn non_streamed_chat(
|
|||
|
||||
for call in meili_calls {
|
||||
let result = match serde_json::from_str(&call.function.arguments) {
|
||||
Ok(SearchInIndexParameters { index_uid, q }) => process_search_request(
|
||||
&index_scheduler,
|
||||
auth_ctrl.clone(),
|
||||
&search_queue,
|
||||
auth_token,
|
||||
index_uid,
|
||||
q,
|
||||
)
|
||||
.await
|
||||
.map_err(|e| e.to_string()),
|
||||
Ok(SearchInIndexParameters { index_uid, q, filter }) => {
|
||||
process_search_request(
|
||||
&index_scheduler,
|
||||
auth_ctrl.clone(),
|
||||
&search_queue,
|
||||
auth_token,
|
||||
index_uid,
|
||||
q,
|
||||
filter,
|
||||
)
|
||||
.await
|
||||
.map_err(|e| e.to_string())
|
||||
}
|
||||
Err(err) => Err(err.to_string()),
|
||||
};
|
||||
|
||||
|
@ -691,13 +723,14 @@ async fn handle_meili_tools(
|
|||
let mut error = None;
|
||||
|
||||
let result = match serde_json::from_str(&call.function.arguments) {
|
||||
Ok(SearchInIndexParameters { index_uid, q }) => match process_search_request(
|
||||
Ok(SearchInIndexParameters { index_uid, q, filter }) => match process_search_request(
|
||||
index_scheduler,
|
||||
auth_ctrl.clone(),
|
||||
search_queue,
|
||||
auth_token,
|
||||
index_uid,
|
||||
q,
|
||||
filter,
|
||||
)
|
||||
.await
|
||||
{
|
||||
|
@ -773,4 +806,42 @@ struct SearchInIndexParameters {
|
|||
index_uid: String,
|
||||
/// The query parameter to use.
|
||||
q: Option<String>,
|
||||
/// The filter parameter to use.
|
||||
filter: Option<String>,
|
||||
}
|
||||
|
||||
fn format_facet_distributions(
|
||||
index: &Index,
|
||||
rtxn: &RoTxn,
|
||||
max_values_per_facet: usize,
|
||||
) -> meilisearch_types::milli::Result<String> {
|
||||
let universe = index.documents_ids(&rtxn)?;
|
||||
let rules = index.filterable_attributes_rules(&rtxn)?;
|
||||
let fields_ids_map = index.fields_ids_map(&rtxn)?;
|
||||
let filterable_attributes = fields_ids_map
|
||||
.names()
|
||||
.filter(|name| rules.iter().any(|rule| rule.match_str(name).matches()))
|
||||
.map(|name| (name, OrderBy::Count));
|
||||
let facets_distribution = index
|
||||
.facets_distribution(&rtxn)
|
||||
.max_values_per_facet(max_values_per_facet)
|
||||
.candidates(universe)
|
||||
.facets(filterable_attributes)
|
||||
.execute()?;
|
||||
|
||||
let mut output = String::new();
|
||||
for (facet_name, entries) in facets_distribution {
|
||||
let _ = write!(&mut output, "{}: ", facet_name);
|
||||
let total_entries = entries.len();
|
||||
for (i, (value, count)) in entries.into_iter().enumerate() {
|
||||
let _ = if total_entries.saturating_sub(1) == i {
|
||||
write!(&mut output, "{} ({}).", value, count)
|
||||
} else {
|
||||
write!(&mut output, "{} ({}), ", value, count)
|
||||
};
|
||||
}
|
||||
let _ = writeln!(&mut output);
|
||||
}
|
||||
|
||||
Ok(output)
|
||||
}
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue