Files
kyle 8b26776cdd feat(search): P3.1 filters and multi-query merge
Native include/exclude domains, time_range, topic, exact_match, min_score,
and up to 4 queries fused with RRF. Honesty notes stay off the Warn/fail
path. Tavily keeps include_answer false and sets auto_parameters false.
Cache key is canonical JSON. CLI flags and skill recipe included.
2026-09-29 15:30:19 -07:00

140 lines
3.5 KiB
Go

package search
import (
"bytes"
"context"
"encoding/json"
"io"
"net/http"
"git.wntrmute.dev/kyle/sift/internal/search/dial"
)
// Tavily is POST {url} JSON. Never requests or returns answer.
type Tavily struct {
Client *dial.Client
Key string
}
func (s *Tavily) Name() string { return NameTavily }
func (s *Tavily) Ready() bool { return s != nil && s.Client.Ready() }
func (s *Tavily) Search(ctx context.Context, query string, k int, f Filter) SourceOut {
if s == nil || s.Client == nil {
return SourceOut{Warn: NameTavily + ": error"}
}
if w := pinErr(ctx, s.Client, NameTavily); w != "" {
return SourceOut{Warn: w}
}
if k <= 0 {
k = DefaultK
}
if k > 20 {
k = 20
}
payload, _ := json.Marshal(tavilyBody(query, k, f))
req, err := http.NewRequestWithContext(ctx, http.MethodPost, s.Client.URL.String(), bytes.NewReader(payload))
if err != nil {
return SourceOut{Warn: warnErr(NameTavily, err)}
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Authorization", "Bearer "+s.Key)
resp, err := s.Client.HTTP.Do(req)
if err != nil {
return SourceOut{Warn: warnErr(NameTavily, err)}
}
if resp.StatusCode != 200 {
code := resp.StatusCode
resp.Body.Close()
return SourceOut{Warn: warnStatus(NameTavily, code)}
}
raw, err := io.ReadAll(io.LimitReader(resp.Body, 1<<20))
resp.Body.Close()
if err != nil {
return SourceOut{Warn: warnErr(NameTavily, err)}
}
hits, credits, err := mapTavily(raw)
if err != nil {
return SourceOut{Warn: NameTavily + ": error"}
}
return SourceOut{Hits: hits, Credits: credits}
}
func tavilyBody(query string, k int, f Filter) map[string]any {
body := map[string]any{
"query": query,
"max_results": k,
"include_answer": false,
"include_raw_content": false,
"include_images": false,
"search_depth": "basic",
"auto_parameters": false,
}
if len(f.IncludeDomains) > 0 {
body["include_domains"] = f.IncludeDomains
mode := f.IncludeDomainsMode
if mode == "" {
mode = "restrict"
}
body["include_domains_mode"] = mode
}
if len(f.ExcludeDomains) > 0 {
body["exclude_domains"] = f.ExcludeDomains
}
if f.TimeRange != "" {
body["time_range"] = f.TimeRange
} else {
if f.StartDate != "" {
body["start_date"] = f.StartDate
}
if f.EndDate != "" {
body["end_date"] = f.EndDate
}
}
if f.Topic != "" && f.Topic != "general" {
body["topic"] = f.Topic
}
if f.ExactMatch {
body["exact_match"] = true
}
if f.Topic == "news" || f.TimeRange != "" || f.StartDate != "" || f.EndDate != "" {
body["include_published_date"] = true
}
return body
}
func mapTavily(raw []byte) ([]Hit, int, error) {
var env struct {
Answer string `json:"answer"`
Results []struct {
URL string `json:"url"`
Title string `json:"title"`
Content string `json:"content"`
Score float64 `json:"score"`
PublishedDate string `json:"published_date"`
} `json:"results"`
Usage struct {
Credits int `json:"credits"`
} `json:"usage"`
}
if err := json.Unmarshal(raw, &env); err != nil {
return nil, 0, err
}
_ = env.Answer // dropped; never returned
hits := make([]Hit, 0, len(env.Results))
for _, r := range env.Results {
if r.URL == "" {
continue
}
hits = append(hits, Hit{
URL: r.URL, Title: r.Title, Snippet: r.Content,
Score: r.Score, Source: NameTavily, PublishedDate: r.PublishedDate,
})
}
credits := env.Usage.Credits
if credits <= 0 {
credits = 1
}
return hits, credits, nil
}