trieve_ruby_client 0.8.2 → 0.10.7

data/docs/MatchCondition.md

@@ -14,6 +14,7 @@ require 'trieve_ruby_client'
 TrieveRubyClient::MatchCondition.openapi_one_of
 # =>
 # [
+#   :'Float',
 #   :'Integer',
 #   :'String'
 # ]
@@ -29,7 +30,7 @@ Find the appropriate object from the `openapi_one_of` list and casts the data in
 require 'trieve_ruby_client'
 
 TrieveRubyClient::MatchCondition.build(data)
-# => #<Integer:0x00007fdd4aab02a0>
+# => #<Float:0x00007fdd4aab02a0>
 
 TrieveRubyClient::MatchCondition.build(data_that_doesnt_match)
 # => nil
@@ -43,6 +44,7 @@ TrieveRubyClient::MatchCondition.build(data_that_doesnt_match)
 
 #### Return type
 
+- `Float`
 - `Integer`
 - `String`
 - `nil` (if no type matches)

data/docs/MessageApi.md

@@ -4,19 +4,19 @@ All URIs are relative to *https://api.trieve.ai*
 
 | Method | HTTP request | Description |
 | ------ | ------------ | ----------- |
-| [**create_message_completion_handler**](MessageApi.md#create_message_completion_handler) | **POST** /api/message | Create a message |
-| [**edit_message_handler**](MessageApi.md#edit_message_handler) | **PUT** /api/message | Edit a message |
+| [**create_message**](MessageApi.md#create_message) | **POST** /api/message | Create message |
+| [**edit_message**](MessageApi.md#edit_message) | **PUT** /api/message | Edit message |
 | [**get_all_topic_messages**](MessageApi.md#get_all_topic_messages) | **GET** /api/messages/{messages_topic_id} | Get all messages for a given topic |
-| [**regenerate_message_handler**](MessageApi.md#regenerate_message_handler) | **DELETE** /api/message | Regenerate message |
+| [**regenerate_message**](MessageApi.md#regenerate_message) | **DELETE** /api/message | Regenerate message |
 
 
-## create_message_completion_handler
+## create_message
 
-> String create_message_completion_handler(tr_dataset, create_message_data)
+> String create_message(tr_dataset, create_message_req_payload)
 
-Create a message
+Create message
 
-Create a message  Create a message. Messages are attached to topics in order to coordinate memory of gen-AI chat sessions. We are considering refactoring this resource of the API soon. Currently, you can only send user messages. If the topic is a RAG topic then the response will include Chunks first on the stream. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information.
+Create message  Create message. Messages are attached to topics in order to coordinate memory of gen-AI chat sessions. We are considering refactoring this resource of the API soon. Currently, you can only send user messages. If the topic is a RAG topic then the response will include Chunks first on the stream. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information. Auth'ed user or api key must have an admin or owner role for the specified dataset's organization.
 
 ### Examples
 
@@ -33,32 +33,32 @@ end
 
 api_instance = TrieveRubyClient::MessageApi.new
 tr_dataset = 'tr_dataset_example' # String | The dataset id to use for the request
-create_message_data = TrieveRubyClient::CreateMessageData.new({new_message_content: 'new_message_content_example', topic_id: 'topic_id_example'}) # CreateMessageData | JSON request payload to create a message completion
+create_message_req_payload = TrieveRubyClient::CreateMessageReqPayload.new({new_message_content: 'new_message_content_example', topic_id: 'topic_id_example'}) # CreateMessageReqPayload | JSON request payload to create a message completion
 
 begin
-  # Create a message
-  result = api_instance.create_message_completion_handler(tr_dataset, create_message_data)
+  # Create message
+  result = api_instance.create_message(tr_dataset, create_message_req_payload)
   p result
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling MessageApi->create_message_completion_handler: #{e}"
+  puts "Error when calling MessageApi->create_message: #{e}"
 end
 ```
 
-#### Using the create_message_completion_handler_with_http_info variant
+#### Using the create_message_with_http_info variant
 
 This returns an Array which contains the response data, status code and headers.
 
-> <Array(String, Integer, Hash)> create_message_completion_handler_with_http_info(tr_dataset, create_message_data)
+> <Array(String, Integer, Hash)> create_message_with_http_info(tr_dataset, create_message_req_payload)
 
 ```ruby
 begin
-  # Create a message
-  data, status_code, headers = api_instance.create_message_completion_handler_with_http_info(tr_dataset, create_message_data)
+  # Create message
+  data, status_code, headers = api_instance.create_message_with_http_info(tr_dataset, create_message_req_payload)
   p status_code # => 2xx
   p headers # => { ... }
   p data # => String
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling MessageApi->create_message_completion_handler_with_http_info: #{e}"
+  puts "Error when calling MessageApi->create_message_with_http_info: #{e}"
 end
 ```
 
@@ -67,7 +67,7 @@ end
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **tr_dataset** | **String** | The dataset id to use for the request |  |
-| **create_message_data** | [**CreateMessageData**](CreateMessageData.md) | JSON request payload to create a message completion |  |
+| **create_message_req_payload** | [**CreateMessageReqPayload**](CreateMessageReqPayload.md) | JSON request payload to create a message completion |  |
 
 ### Return type
 
@@ -83,13 +83,13 @@ end
 - **Accept**: text/plain, application/json
 
 
-## edit_message_handler
+## edit_message
 
-> edit_message_handler(tr_dataset, edit_message_data)
+> edit_message(tr_dataset, edit_message_req_payload)
 
-Edit a message
+Edit message
 
-Edit a message  Edit a message which exists within the topic's chat history. This will delete the message and replace it with a new message. The new message will be generated by the AI based on the new content provided in the request body. The response will include Chunks first on the stream if the topic is using RAG. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information.
+Edit message  Edit message which exists within the topic's chat history. This will delete the message and replace it with a new message. The new message will be generated by the AI based on the new content provided in the request body. The response will include Chunks first on the stream if the topic is using RAG. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information. Auth'ed user or api key must have an admin or owner role for the specified dataset's organization.
 
 ### Examples
 
@@ -106,31 +106,31 @@ end
 
 api_instance = TrieveRubyClient::MessageApi.new
 tr_dataset = 'tr_dataset_example' # String | The dataset id to use for the request
-edit_message_data = TrieveRubyClient::EditMessageData.new({message_sort_order: 37, new_message_content: 'new_message_content_example', topic_id: 'topic_id_example'}) # EditMessageData | JSON request payload to edit a message and get a new stream
+edit_message_req_payload = TrieveRubyClient::EditMessageReqPayload.new({message_sort_order: 37, new_message_content: 'new_message_content_example', topic_id: 'topic_id_example'}) # EditMessageReqPayload | JSON request payload to edit a message and get a new stream
 
 begin
-  # Edit a message
-  api_instance.edit_message_handler(tr_dataset, edit_message_data)
+  # Edit message
+  api_instance.edit_message(tr_dataset, edit_message_req_payload)
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling MessageApi->edit_message_handler: #{e}"
+  puts "Error when calling MessageApi->edit_message: #{e}"
 end
 ```
 
-#### Using the edit_message_handler_with_http_info variant
+#### Using the edit_message_with_http_info variant
 
 This returns an Array which contains the response data (`nil` in this case), status code and headers.
 
-> <Array(nil, Integer, Hash)> edit_message_handler_with_http_info(tr_dataset, edit_message_data)
+> <Array(nil, Integer, Hash)> edit_message_with_http_info(tr_dataset, edit_message_req_payload)
 
 ```ruby
 begin
-  # Edit a message
-  data, status_code, headers = api_instance.edit_message_handler_with_http_info(tr_dataset, edit_message_data)
+  # Edit message
+  data, status_code, headers = api_instance.edit_message_with_http_info(tr_dataset, edit_message_req_payload)
   p status_code # => 2xx
   p headers # => { ... }
   p data # => nil
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling MessageApi->edit_message_handler_with_http_info: #{e}"
+  puts "Error when calling MessageApi->edit_message_with_http_info: #{e}"
 end
 ```
 
@@ -139,7 +139,7 @@ end
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **tr_dataset** | **String** | The dataset id to use for the request |  |
-| **edit_message_data** | [**EditMessageData**](EditMessageData.md) | JSON request payload to edit a message and get a new stream |  |
+| **edit_message_req_payload** | [**EditMessageReqPayload**](EditMessageReqPayload.md) | JSON request payload to edit a message and get a new stream |  |
 
 ### Return type
 
@@ -228,13 +228,13 @@ end
 - **Accept**: application/json
 
 
-## regenerate_message_handler
+## regenerate_message
 
-> String regenerate_message_handler(tr_dataset, regenerate_message_data)
+> String regenerate_message(tr_dataset, regenerate_message_req_payload)
 
 Regenerate message
 
-Regenerate message  Regenerate the assistant response to the last user message of a topic. This will delete the last message and replace it with a new message. The response will include Chunks first on the stream if the topic is using RAG. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information.
+Regenerate message  Regenerate the assistant response to the last user message of a topic. This will delete the last message and replace it with a new message. The response will include Chunks first on the stream if the topic is using RAG. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information. Auth'ed user or api key must have an admin or owner role for the specified dataset's organization.
 
 ### Examples
 
@@ -251,32 +251,32 @@ end
 
 api_instance = TrieveRubyClient::MessageApi.new
 tr_dataset = 'tr_dataset_example' # String | The dataset id to use for the request
-regenerate_message_data = TrieveRubyClient::RegenerateMessageData.new({topic_id: 'topic_id_example'}) # RegenerateMessageData | JSON request payload to delete an agent message then regenerate it in a strem
+regenerate_message_req_payload = TrieveRubyClient::RegenerateMessageReqPayload.new({topic_id: 'topic_id_example'}) # RegenerateMessageReqPayload | JSON request payload to delete an agent message then regenerate it in a strem
 
 begin
   # Regenerate message
-  result = api_instance.regenerate_message_handler(tr_dataset, regenerate_message_data)
+  result = api_instance.regenerate_message(tr_dataset, regenerate_message_req_payload)
   p result
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling MessageApi->regenerate_message_handler: #{e}"
+  puts "Error when calling MessageApi->regenerate_message: #{e}"
 end
 ```
 
-#### Using the regenerate_message_handler_with_http_info variant
+#### Using the regenerate_message_with_http_info variant
 
 This returns an Array which contains the response data, status code and headers.
 
-> <Array(String, Integer, Hash)> regenerate_message_handler_with_http_info(tr_dataset, regenerate_message_data)
+> <Array(String, Integer, Hash)> regenerate_message_with_http_info(tr_dataset, regenerate_message_req_payload)
 
 ```ruby
 begin
   # Regenerate message
-  data, status_code, headers = api_instance.regenerate_message_handler_with_http_info(tr_dataset, regenerate_message_data)
+  data, status_code, headers = api_instance.regenerate_message_with_http_info(tr_dataset, regenerate_message_req_payload)
   p status_code # => 2xx
   p headers # => { ... }
   p data # => String
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling MessageApi->regenerate_message_handler_with_http_info: #{e}"
+  puts "Error when calling MessageApi->regenerate_message_with_http_info: #{e}"
 end
 ```
 
@@ -285,7 +285,7 @@ end
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **tr_dataset** | **String** | The dataset id to use for the request |  |
-| **regenerate_message_data** | [**RegenerateMessageData**](RegenerateMessageData.md) | JSON request payload to delete an agent message then regenerate it in a strem |  |
+| **regenerate_message_req_payload** | [**RegenerateMessageReqPayload**](RegenerateMessageReqPayload.md) | JSON request payload to delete an agent message then regenerate it in a strem |  |
 
 ### Return type
 

data/docs/Organization.md

@@ -5,6 +5,7 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **created_at** | **Time** |  |  |
+| **deleted** | **Integer** |  |  |
 | **id** | **String** |  |  |
 | **name** | **String** |  |  |
 | **registerable** | **Boolean** |  | [optional] |
@@ -17,6 +18,7 @@ require 'trieve_ruby_client'
 
 instance = TrieveRubyClient::Organization.new(
   created_at: null,
+  deleted: null,
   id: null,
   name: null,
   registerable: null,

data/docs/OrganizationApi.md

@@ -5,8 +5,8 @@ All URIs are relative to *https://api.trieve.ai*
 | Method | HTTP request | Description |
 | ------ | ------------ | ----------- |
 | [**create_organization**](OrganizationApi.md#create_organization) | **POST** /api/organization | Create Organization |
-| [**delete_organization_by_id**](OrganizationApi.md#delete_organization_by_id) | **DELETE** /api/organization/{organization_id} | Delete Organization |
-| [**get_organization_by_id**](OrganizationApi.md#get_organization_by_id) | **GET** /api/organization/{organization_id} | Get Organization |
+| [**delete_organization**](OrganizationApi.md#delete_organization) | **DELETE** /api/organization/{organization_id} | Delete Organization |
+| [**get_organization**](OrganizationApi.md#get_organization) | **GET** /api/organization/{organization_id} | Get Organization |
 | [**get_organization_usage**](OrganizationApi.md#get_organization_usage) | **GET** /api/organization/usage/{organization_id} | Get Organization Usage |
 | [**get_organization_users**](OrganizationApi.md#get_organization_users) | **GET** /api/organization/users/{organization_id} | Get Organization Users |
 | [**update_organization**](OrganizationApi.md#update_organization) | **PUT** /api/organization | Update Organization |
@@ -83,9 +83,9 @@ end
 - **Accept**: application/json
 
 
-## delete_organization_by_id
+## delete_organization
 
-> <Organization> delete_organization_by_id(tr_organization, organization_id)
+> delete_organization(tr_organization, organization_id)
 
 Delete Organization
 
@@ -110,28 +110,27 @@ organization_id = '38400000-8cf0-11bd-b23e-10b96e4ef00d' # String | The id of th
 
 begin
   # Delete Organization
-  result = api_instance.delete_organization_by_id(tr_organization, organization_id)
-  p result
+  api_instance.delete_organization(tr_organization, organization_id)
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling OrganizationApi->delete_organization_by_id: #{e}"
+  puts "Error when calling OrganizationApi->delete_organization: #{e}"
 end
 ```
 
-#### Using the delete_organization_by_id_with_http_info variant
+#### Using the delete_organization_with_http_info variant
 
-This returns an Array which contains the response data, status code and headers.
+This returns an Array which contains the response data (`nil` in this case), status code and headers.
 
-> <Array(<Organization>, Integer, Hash)> delete_organization_by_id_with_http_info(tr_organization, organization_id)
+> <Array(nil, Integer, Hash)> delete_organization_with_http_info(tr_organization, organization_id)
 
 ```ruby
 begin
   # Delete Organization
-  data, status_code, headers = api_instance.delete_organization_by_id_with_http_info(tr_organization, organization_id)
+  data, status_code, headers = api_instance.delete_organization_with_http_info(tr_organization, organization_id)
   p status_code # => 2xx
   p headers # => { ... }
-  p data # => <Organization>
+  p data # => nil
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling OrganizationApi->delete_organization_by_id_with_http_info: #{e}"
+  puts "Error when calling OrganizationApi->delete_organization_with_http_info: #{e}"
 end
 ```
 
@@ -144,7 +143,7 @@ end
 
 ### Return type
 
-[**Organization**](Organization.md)
+nil (empty response body)
 
 ### Authorization
 
@@ -156,13 +155,13 @@ end
 - **Accept**: application/json
 
 
-## get_organization_by_id
+## get_organization
 
-> <Organization> get_organization_by_id(tr_organization, organization_id)
+> <Organization> get_organization(tr_organization, organization_id)
 
 Get Organization
 
-Get Organization  Fetch the details of an organization by its id. The auth'ed user must be an admin or owner of the organization to fetch it.
+Get Organization  Fetch the details of an organization by its id. Auth'ed user or api key must have an admin or owner role for the specified dataset's organization.
 
 ### Examples
 
@@ -183,28 +182,28 @@ organization_id = '38400000-8cf0-11bd-b23e-10b96e4ef00d' # String | The id of th
 
 begin
   # Get Organization
-  result = api_instance.get_organization_by_id(tr_organization, organization_id)
+  result = api_instance.get_organization(tr_organization, organization_id)
   p result
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling OrganizationApi->get_organization_by_id: #{e}"
+  puts "Error when calling OrganizationApi->get_organization: #{e}"
 end
 ```
 
-#### Using the get_organization_by_id_with_http_info variant
+#### Using the get_organization_with_http_info variant
 
 This returns an Array which contains the response data, status code and headers.
 
-> <Array(<Organization>, Integer, Hash)> get_organization_by_id_with_http_info(tr_organization, organization_id)
+> <Array(<Organization>, Integer, Hash)> get_organization_with_http_info(tr_organization, organization_id)
 
 ```ruby
 begin
   # Get Organization
-  data, status_code, headers = api_instance.get_organization_by_id_with_http_info(tr_organization, organization_id)
+  data, status_code, headers = api_instance.get_organization_with_http_info(tr_organization, organization_id)
   p status_code # => 2xx
   p headers # => { ... }
   p data # => <Organization>
 rescue TrieveRubyClient::ApiError => e
-  puts "Error when calling OrganizationApi->get_organization_by_id_with_http_info: #{e}"
+  puts "Error when calling OrganizationApi->get_organization_with_http_info: #{e}"
 end
 ```
 
@@ -235,7 +234,7 @@ end
 
 Get Organization Usage
 
-Get Organization Usage  Fetch the current usage specification of an organization by its id. The auth'ed user must be an admin or owner of the organization to fetch it.
+Get Organization Usage  Fetch the current usage specification of an organization by its id. Auth'ed user or api key must have an admin or owner role for the specified dataset's organization.
 
 ### Examples
 
@@ -308,7 +307,7 @@ end
 
 Get Organization Users
 
-Get Organization Users  Fetch the users of an organization by its id. The auth'ed user must be an admin or owner of the organization to fetch it.
+Get Organization Users  Fetch the users of an organization by its id. Auth'ed user or api key must have an admin or owner role for the specified dataset's organization.
 
 ### Examples
 

data/docs/RangeCondition.md

@@ -15,8 +15,7 @@ TrieveRubyClient::RangeCondition.openapi_one_of
 # =>
 # [
 #   :'Float',
-#   :'Integer',
-#   :'String'
+#   :'Integer'
 # ]
 ```
 
@@ -46,6 +45,5 @@ TrieveRubyClient::RangeCondition.build(data_that_doesnt_match)
 
 - `Float`
 - `Integer`
-- `String`
 - `nil` (if no type matches)
 

data/docs/RegenerateMessageReqPayload.md

@@ -0,0 +1,40 @@
+# TrieveRubyClient::RegenerateMessageReqPayload
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **completion_first** | **Boolean** | Completion first decides whether the stream should contain the stream of the completion response or the chunks first. Default is false. Keep in mind that || is used to separate the chunks from the completion response. If || is in the completion then you may want to split on ||{ instead. | [optional] |
+| **filters** | [**ChunkFilter**](ChunkFilter.md) |  | [optional] |
+| **frequency_penalty** | **Float** | Frequency penalty is a number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. Default is 0.7. | [optional] |
+| **highlight_citations** | **Boolean** | Whether or not to highlight the citations in the response. If this is set to true or not included, the citations will be highlighted. If this is set to false, the citations will not be highlighted. Default is true. | [optional] |
+| **highlight_delimiters** | **Array<String>** | The delimiters to use for highlighting the citations. If this is not included, the default delimiters will be used. Default is `[\".\", \"!\", \"?\", \"\\n\", \"\\t\", \",\"]`. | [optional] |
+| **max_tokens** | **Integer** | The maximum number of tokens to generate in the chat completion. | [optional] |
+| **presence_penalty** | **Float** | Presence penalty is a number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. | [optional] |
+| **search_type** | **String** | Search_type can be either \"semantic\", \"fulltext\", or \"hybrid\". \"hybrid\" will pull in one page (10 chunks) of both semantic and full-text results then re-rank them using BAAI/bge-reranker-large. \"semantic\" will pull in one page (10 chunks) of the nearest cosine distant vectors. \"fulltext\" will pull in one page (10 chunks) of full-text results based on SPLADE. | [optional] |
+| **stop_tokens** | **Array<String>** | Stop tokens are up to 4 sequences where the API will stop generating further tokens. | [optional] |
+| **stream_response** | **Boolean** | Whether or not to stream the response. If this is set to true or not included, the response will be a stream. If this is set to false, the response will be a normal JSON response. Default is true. | [optional] |
+| **temperature** | **Float** | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Default is 0.7. | [optional] |
+| **topic_id** | **String** | The id of the topic to regenerate the last message for. |  |
+
+## Example
+
+```ruby
+require 'trieve_ruby_client'
+
+instance = TrieveRubyClient::RegenerateMessageReqPayload.new(
+  completion_first: null,
+  filters: null,
+  frequency_penalty: null,
+  highlight_citations: null,
+  highlight_delimiters: null,
+  max_tokens: null,
+  presence_penalty: null,
+  search_type: null,
+  stop_tokens: null,
+  stream_response: null,
+  temperature: null,
+  topic_id: null
+)
+```
+

data/docs/RemoveChunkFromGroupReqPayload.md

@@ -0,0 +1,18 @@
+# TrieveRubyClient::RemoveChunkFromGroupReqPayload
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **chunk_id** | **String** | Id of the chunk to remove from the group. |  |
+
+## Example
+
+```ruby
+require 'trieve_ruby_client'
+
+instance = TrieveRubyClient::RemoveChunkFromGroupReqPayload.new(
+  chunk_id: null
+)
+```
+

data/docs/ScoreChunkDTO.md

@@ -4,7 +4,8 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **metadata** | [**Array<ChunkMetadata>**](ChunkMetadata.md) |  |  |
+| **highlights** | **Array<String>** |  | [optional] |
+| **metadata** | [**Array<ChunkMetadataTypes>**](ChunkMetadataTypes.md) |  |  |
 | **score** | **Float** |  |  |
 
 ## Example
@@ -13,6 +14,7 @@
 require 'trieve_ruby_client'
 
 instance = TrieveRubyClient::ScoreChunkDTO.new(
+  highlights: null,
   metadata: null,
   score: null
 )

data/docs/SearchChunkData.md

@@ -4,18 +4,21 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
+| **content_only** | **Boolean** | Set content_only to true to only returning the chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typically 10-50ms). Default is false. | [optional] |
 | **filters** | [**ChunkFilter**](ChunkFilter.md) |  | [optional] |
 | **get_collisions** | **Boolean** | Set get_collisions to true to get the collisions for each chunk. This will only apply if environment variable COLLISIONS_ENABLED is set to true. | [optional] |
 | **get_total_pages** | **Boolean** | Get total page count for the query accounting for the applied filters. Defaults to false, but can be set to true when the latency penalty is acceptable (typically 50-200ms). | [optional] |
 | **highlight_delimiters** | **Array<String>** | Set highlight_delimiters to a list of strings to use as delimiters for highlighting. If not specified, this defaults to [\"?\", \",\", \".\", \"!\"]. | [optional] |
-| **highlight_results** | **Boolean** | Set highlight_results to false for a slight latency improvement (1-10ms). If not specified, this defaults to true. This will add <b><mark> tags to the chunk_html of the chunks to highlight matching sub-sentences. | [optional] |
+| **highlight_results** | **Boolean** | Set highlight_results to false for a slight latency improvement (1-10ms). If not specified, this defaults to true. This will add `<b><mark>` tags to the chunk_html of the chunks to highlight matching sub-sentences. | [optional] |
+| **highlight_threshold** | **Float** | Set highlight_threshold to a lower or higher value to adjust the sensitivity of the highlights applied to the chunk html. If not specified, this defaults to 0.8. The range is 0.0 to 1.0. | [optional] |
 | **page** | **Integer** | Page of chunks to fetch. Page is 1-indexed. | [optional] |
 | **page_size** | **Integer** | Page size is the number of chunks to fetch. This can be used to fetch more than 10 chunks at a time. | [optional] |
 | **query** | **String** | Query is the search query. This can be any string. The query will be used to create an embedding vector and/or SPLADE vector which will be used to find the result set. |  |
 | **recency_bias** | **Float** | Recency Bias lets you determine how much of an effect the recency of chunks will have on the search results. If not specified, this defaults to 0.0. We recommend setting this to 1.0 for a gentle reranking of the results, >3.0 for a strong reranking of the results. | [optional] |
 | **score_threshold** | **Float** | Set score_threshold to a float to filter out chunks with a score below the threshold. | [optional] |
-| **search_type** | **String** | Can be either \"semantic\", \"fulltext\", or \"hybrid\". \"hybrid\" will pull in one page (10 chunks) of both semantic and full-text results then re-rank them using BAAI/bge-reranker-large. \"semantic\" will pull in one page (10 chunks) of the nearest cosine distant vectors. \"fulltext\" will pull in one page (10 chunks) of full-text results based on SPLADE. |  |
-| **slim_chunks** | **Boolean** | Set slim_chunks to true to avoid returning the content and chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typicall 10-50ms). Default is false. | [optional] |
+| **search_type** | **String** | Can be either \"semantic\", \"fulltext\", or \"hybrid\". If specified as \"hybrid\", it will pull in one page (10 chunks) of both semantic and full-text results then re-rank them using BAAI/bge-reranker-large. \"semantic\" will pull in one page (10 chunks) of the nearest cosine distant vectors. \"fulltext\" will pull in one page (10 chunks) of full-text results based on SPLADE. |  |
+| **slim_chunks** | **Boolean** | Set slim_chunks to true to avoid returning the content and chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typically 10-50ms). Default is false. | [optional] |
+| **tag_weights** | **Hash<String, Float>** | Tag weights is a JSON object which can be used to boost the ranking of chunks with certain tags. This is useful for when you want to be able to bias towards chunks with a certain tag on the fly. The keys are the tag names and the values are the weights. | [optional] |
 | **use_weights** | **Boolean** | Set use_weights to true to use the weights of the chunks in the result set in order to sort them. If not specified, this defaults to true. | [optional] |
 
 ## Example
@@ -24,11 +27,13 @@
 require 'trieve_ruby_client'
 
 instance = TrieveRubyClient::SearchChunkData.new(
+  content_only: null,
   filters: null,
   get_collisions: null,
   get_total_pages: null,
   highlight_delimiters: null,
   highlight_results: null,
+  highlight_threshold: null,
   page: null,
   page_size: null,
   query: null,
@@ -36,6 +41,7 @@ instance = TrieveRubyClient::SearchChunkData.new(
   score_threshold: null,
   search_type: null,
   slim_chunks: null,
+  tag_weights: null,
   use_weights: null
 )
 ```

data/docs/SearchChunksReqPayload.md

@@ -0,0 +1,54 @@
+# TrieveRubyClient::SearchChunksReqPayload
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **content_only** | **Boolean** | Set content_only to true to only returning the chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typically 10-50ms). Default is false. | [optional] |
+| **filters** | [**ChunkFilter**](ChunkFilter.md) |  | [optional] |
+| **get_collisions** | **Boolean** | Set get_collisions to true to get the collisions for each chunk. This will only apply if environment variable COLLISIONS_ENABLED is set to true. | [optional] |
+| **get_total_pages** | **Boolean** | Get total page count for the query accounting for the applied filters. Defaults to false, but can be set to true when the latency penalty is acceptable (typically 50-200ms). | [optional] |
+| **highlight_delimiters** | **Array<String>** | Set highlight_delimiters to a list of strings to use as delimiters for highlighting. If not specified, this defaults to [\"?\", \",\", \".\", \"!\"]. These are the characters that will be used to split the chunk_html into splits for highlighting. These are the characters that will be used to split the chunk_html into splits for highlighting. | [optional] |
+| **highlight_max_length** | **Integer** | Set highlight_max_length to control the maximum number of tokens (typically whitespace separated strings, but sometimes also word stems) which can be present within a single highlight. If not specified, this defaults to 8. This is useful to shorten large splits which may have low scores due to length compared to the query. Set to something very large like 100 to highlight entire splits. | [optional] |
+| **highlight_max_num** | **Integer** | Set highlight_max_num to control the maximum number of highlights per chunk. If not specified, this defaults to 3. It may be less than 3 if no snippets score above the highlight_threshold. | [optional] |
+| **highlight_results** | **Boolean** | Set highlight_results to false for a slight latency improvement (1-10ms). If not specified, this defaults to true. This will add `<b><mark>` tags to the chunk_html of the chunks to highlight matching splits and return the highlights on each scored chunk in the response. | [optional] |
+| **highlight_threshold** | **Float** | Set highlight_threshold to a lower or higher value to adjust the sensitivity of the highlights applied to the chunk html. If not specified, this defaults to 0.8. The range is 0.0 to 1.0. | [optional] |
+| **highlight_window** | **Integer** | Set highlight_window to a number to control the amount of words that are returned around the matched phrases. If not specified, this defaults to 0. This is useful for when you want to show more context around the matched words. When specified, window/2 whitespace separated words are added before and after each highlight in the response's highlights array. If an extended highlight overlaps with another highlight, the overlapping words are only included once. | [optional] |
+| **page** | **Integer** | Page of chunks to fetch. Page is 1-indexed. | [optional] |
+| **page_size** | **Integer** | Page size is the number of chunks to fetch. This can be used to fetch more than 10 chunks at a time. | [optional] |
+| **query** | **String** | Query is the search query. This can be any string. The query will be used to create an embedding vector and/or SPLADE vector which will be used to find the result set. |  |
+| **recency_bias** | **Float** | Recency Bias lets you determine how much of an effect the recency of chunks will have on the search results. If not specified, this defaults to 0.0. We recommend setting this to 1.0 for a gentle reranking of the results, >3.0 for a strong reranking of the results. | [optional] |
+| **score_threshold** | **Float** | Set score_threshold to a float to filter out chunks with a score below the threshold. | [optional] |
+| **search_type** | **String** | Can be either \"semantic\", \"fulltext\", or \"hybrid\". If specified as \"hybrid\", it will pull in one page (10 chunks) of both semantic and full-text results then re-rank them using BAAI/bge-reranker-large. \"semantic\" will pull in one page (10 chunks) of the nearest cosine distant vectors. \"fulltext\" will pull in one page (10 chunks) of full-text results based on SPLADE. |  |
+| **slim_chunks** | **Boolean** | Set slim_chunks to true to avoid returning the content and chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typically 10-50ms). Default is false. | [optional] |
+| **tag_weights** | **Hash<String, Float>** | Tag weights is a JSON object which can be used to boost the ranking of chunks with certain tags. This is useful for when you want to be able to bias towards chunks with a certain tag on the fly. The keys are the tag names and the values are the weights. | [optional] |
+| **use_weights** | **Boolean** | Set use_weights to true to use the weights of the chunks in the result set in order to sort them. If not specified, this defaults to true. | [optional] |
+
+## Example
+
+```ruby
+require 'trieve_ruby_client'
+
+instance = TrieveRubyClient::SearchChunksReqPayload.new(
+  content_only: null,
+  filters: null,
+  get_collisions: null,
+  get_total_pages: null,
+  highlight_delimiters: null,
+  highlight_max_length: null,
+  highlight_max_num: null,
+  highlight_results: null,
+  highlight_threshold: null,
+  highlight_window: null,
+  page: null,
+  page_size: null,
+  query: null,
+  recency_bias: null,
+  score_threshold: null,
+  search_type: null,
+  slim_chunks: null,
+  tag_weights: null,
+  use_weights: null
+)
+```
+

data/docs/SearchOverGroupsData.md

@@ -8,8 +8,12 @@
 | **get_collisions** | **Boolean** | Set get_collisions to true to get the collisions for each chunk. This will only apply if environment variable COLLISIONS_ENABLED is set to true. | [optional] |
 | **get_total_pages** | **Boolean** | Get total page count for the query accounting for the applied filters. Defaults to false, but can be set to true when the latency penalty is acceptable (typically 50-200ms). | [optional] |
 | **group_size** | **Integer** | Group_size is the number of chunks to fetch for each group. The default is 3. If a group has less than group_size chunks, all chunks will be returned. If this is set to a large number, we recommend setting slim_chunks to true to avoid returning the content and chunk_html of the chunks so as to lower the amount of time required for content download and serialization. | [optional] |
-| **highlight_delimiters** | **Array<String>** | Set highlight_delimiters to a list of strings to use as delimiters for highlighting. If not specified, this defaults to [\"?\", \",\", \".\", \"!\"]. | [optional] |
-| **highlight_results** | **Boolean** | Set highlight_results to false for a slight latency improvement (1-10ms). If not specified, this defaults to true. This will add <b><mark> tags to the chunk_html of the chunks to highlight matching sub-sentences. | [optional] |
+| **highlight_delimiters** | **Array<String>** | Set highlight_delimiters to a list of strings to use as delimiters for highlighting. If not specified, this defaults to [\"?\", \",\", \".\", \"!\"]. These are the characters that will be used to split the chunk_html into splits for highlighting. | [optional] |
+| **highlight_max_length** | **Integer** | Set highlight_max_length to control the maximum number of tokens (typically whitespace separated strings, but sometimes also word stems) which can be present within a single highlight. If not specified, this defaults to 8. This is useful to shorten large splits which may have low scores due to length compared to the query. Set to something very large like 100 to highlight entire splits. | [optional] |
+| **highlight_max_num** | **Integer** | Set highlight_max_num to control the maximum number of highlights per chunk. If not specified, this defaults to 3. It may be less than 3 if no snippets score above the highlight_threshold. | [optional] |
+| **highlight_results** | **Boolean** | Set highlight_results to false for a slight latency improvement (1-10ms). If not specified, this defaults to true. This will add `<b><mark>` tags to the chunk_html of the chunks to highlight matching splits and return the highlights on each scored chunk in the response. | [optional] |
+| **highlight_threshold** | **Float** | Set highlight_threshold to a lower or higher value to adjust the sensitivity of the highlights applied to the chunk html. If not specified, this defaults to 0.8. The range is 0.0 to 1.0. | [optional] |
+| **highlight_window** | **Integer** | Set highlight_window to a number to control the amount of words that are returned around the matched phrases. If not specified, this defaults to 0. This is useful for when you want to show more context around the matched words. When specified, window/2 whitespace separated words are added before and after each highlight in the response's highlights array. If an extended highlight overlaps with another highlight, the overlapping words are only included once. | [optional] |
 | **page** | **Integer** | Page of group results to fetch. Page is 1-indexed. | [optional] |
 | **page_size** | **Integer** | Page size is the number of group results to fetch. The default is 10. | [optional] |
 | **query** | **String** | Query is the search query. This can be any string. The query will be used to create an embedding vector and/or SPLADE vector which will be used to find the result set. |  |
@@ -28,7 +32,11 @@ instance = TrieveRubyClient::SearchOverGroupsData.new(
   get_total_pages: null,
   group_size: null,
   highlight_delimiters: null,
+  highlight_max_length: null,
+  highlight_max_num: null,
   highlight_results: null,
+  highlight_threshold: null,
+  highlight_window: null,
   page: null,
   page_size: null,
   query: null,