...
Formulates a search query optimized for search engines (based on the entire discussion history)
Executes a web search using the configured search engine.
Scraps the HTML content of top web pages returned by the search engine
Divide the scrapped content into small chunks of text
[Optional] Embed the chunks locally and perform a similarity search based on the generated query.
Passes the relevant information to the context and answers the user’s question/query
...
Configuration settings (technical)
Reference in Code
WebSearch
Web Search Config
Provided below is the general structure of the configuration for the Web Search module.
...
Field | Type | Description | Default Value |
---|---|---|---|
query_instruction | str | Instruction of the query parameter | "The user's search query, optimized for search engines, incorporates relevant details from the conversation, especially if it is a follow-up question. Always use the user's language message." |
Configuraion Example
...
Code Block | ||
---|---|---|
| ||
{ "WebSearchConfig": { "model_namedebugging": "AZURE_GPT_4_0613"false, "searchmodel_engine_name": "bingAZURE_GPT_4o_2024_0513", "bing_config": { "search_country_codemarket": "de-CH", "search_marketcountry_code": "de-CH", "custom_search_config": { "id": "your_custom_config_id"null, "boosted_search_domains": [] } }, "search_engine_name": "bing", "data_sources_config": { "fetchchunk_size": 4600, "maxfetch_workerssize": 10, "chunkmax_sizeworkers": 60010, "chunk_overlap": 50, "embedding_batch_size": 128 }, "query_generation_config": { "query_instruction": "The user's search query, optimized for search engines, incorporates relevant details from the conversation, especially if it is a follow-up question. Always use the user's language message." }, "answer_generation_config": { "embedding_reranking": false, "limit_token_sources": 500010000, "max_chunks_to_consider": 20500, "number_history_interactions_included": 4 } } } |
Definition
Code Block | ||
---|---|---|
| ||
{ "type": 2,"function", "function": { "name": "WebSearch", "embedding_reranking "parameters": true{ }"type": "object", "required"query_generation_config: [ "query" ], "properties": { "query_instruction": { "type": "The user"string", "description": "User's searchquery query,that optimizedneeds forto searchbe engines,used incorporatesto relevantretrieve detailsinformation from the conversation, especially if it is a follow-up question. Always use the user's language message." web using a search engine." } } }, "debuggingdescription": false"Useful to answer user's query based on information from the web." } } |
...
Author |
---|