|
| 1 | +// Copyright 2026 The OpenAgent Authors. All Rights Reserved. |
| 2 | +// |
| 3 | +// Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +// you may not use this file except in compliance with the License. |
| 5 | +// You may obtain a copy of the License at |
| 6 | +// |
| 7 | +// http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +// |
| 9 | +// Unless required by applicable law or agreed to in writing, software |
| 10 | +// distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +// See the License for the specific language governing permissions and |
| 13 | +// limitations under the License. |
| 14 | + |
| 15 | +package model |
| 16 | + |
| 17 | +import ( |
| 18 | + "fmt" |
| 19 | + "io" |
| 20 | + "net" |
| 21 | + "net/url" |
| 22 | + "path" |
| 23 | + "regexp" |
| 24 | + "strings" |
| 25 | + "sync" |
| 26 | + |
| 27 | + "github.com/the-open-agent/openagent/txt" |
| 28 | + "golang.org/x/sync/singleflight" |
| 29 | +) |
| 30 | + |
| 31 | +var ( |
| 32 | + fileURLPattern = regexp.MustCompile(`https?://[^\s<>"']+`) |
| 33 | + fileContentCache sync.Map |
| 34 | + fileContentGroup singleflight.Group |
| 35 | +) |
| 36 | + |
| 37 | +type fileContentProvider struct { |
| 38 | + providerType string |
| 39 | + provider ModelProvider |
| 40 | +} |
| 41 | + |
| 42 | +func (p *fileContentProvider) GetPricing() string { |
| 43 | + return p.provider.GetPricing() |
| 44 | +} |
| 45 | + |
| 46 | +func (p *fileContentProvider) ListModels() ([]string, error) { |
| 47 | + return p.provider.ListModels() |
| 48 | +} |
| 49 | + |
| 50 | +func (p *fileContentProvider) QueryText(question string, writer io.Writer, history []*RawMessage, prompt string, knowledgeMessages []*RawMessage, toolSession *ToolSession, lang string) (*ModelResult, error) { |
| 51 | + question, err := replaceFileURLs(question, p.providerType, lang) |
| 52 | + if err != nil { |
| 53 | + return nil, err |
| 54 | + } |
| 55 | + |
| 56 | + history, err = replaceFileURLsInMessages(history, p.providerType, lang) |
| 57 | + if err != nil { |
| 58 | + return nil, err |
| 59 | + } |
| 60 | + |
| 61 | + return p.provider.QueryText(question, writer, history, prompt, knowledgeMessages, toolSession, lang) |
| 62 | +} |
| 63 | + |
| 64 | +func wrapFileContentProvider(providerType string, provider ModelProvider) ModelProvider { |
| 65 | + return &fileContentProvider{ |
| 66 | + providerType: providerType, |
| 67 | + provider: provider, |
| 68 | + } |
| 69 | +} |
| 70 | + |
| 71 | +func replaceFileURLs(text string, providerType string, lang string) (string, error) { |
| 72 | + matches := fileURLPattern.FindAllStringIndex(text, -1) |
| 73 | + var result strings.Builder |
| 74 | + last := 0 |
| 75 | + for _, match := range matches { |
| 76 | + result.WriteString(text[last:match[0]]) |
| 77 | + rawURL := text[match[0]:match[1]] |
| 78 | + if strings.LastIndex(text[:match[0]], "<") > strings.LastIndex(text[:match[0]], ">") { |
| 79 | + result.WriteString(rawURL) |
| 80 | + last = match[1] |
| 81 | + continue |
| 82 | + } |
| 83 | + parsedURL, ext, ok := parseDocumentURL(rawURL) |
| 84 | + if !ok || !shouldReplaceFileURL(providerType, parsedURL) { |
| 85 | + result.WriteString(rawURL) |
| 86 | + last = match[1] |
| 87 | + continue |
| 88 | + } |
| 89 | + |
| 90 | + content, err := getFileContent(rawURL, ext, lang) |
| 91 | + if err != nil { |
| 92 | + return "", err |
| 93 | + } |
| 94 | + fmt.Fprintf(&result, "URL: %s\nContent:\n%s", rawURL, content) |
| 95 | + last = match[1] |
| 96 | + } |
| 97 | + result.WriteString(text[last:]) |
| 98 | + return result.String(), nil |
| 99 | +} |
| 100 | + |
| 101 | +func replaceFileURLsInMessages(messages []*RawMessage, providerType string, lang string) ([]*RawMessage, error) { |
| 102 | + result := make([]*RawMessage, len(messages)) |
| 103 | + for i, message := range messages { |
| 104 | + if message == nil { |
| 105 | + continue |
| 106 | + } |
| 107 | + |
| 108 | + text, err := replaceFileURLs(message.Text, providerType, lang) |
| 109 | + if err != nil { |
| 110 | + return nil, err |
| 111 | + } |
| 112 | + if text == message.Text { |
| 113 | + result[i] = message |
| 114 | + continue |
| 115 | + } |
| 116 | + |
| 117 | + clone := *message |
| 118 | + clone.Text = text |
| 119 | + result[i] = &clone |
| 120 | + } |
| 121 | + return result, nil |
| 122 | +} |
| 123 | + |
| 124 | +func parseDocumentURL(rawURL string) (*url.URL, string, bool) { |
| 125 | + parsedURL, err := url.Parse(rawURL) |
| 126 | + if err != nil || (parsedURL.Scheme != "http" && parsedURL.Scheme != "https") || parsedURL.Hostname() == "" { |
| 127 | + return nil, "", false |
| 128 | + } |
| 129 | + |
| 130 | + ext := strings.ToLower(path.Ext(parsedURL.Path)) |
| 131 | + for _, supportedExt := range txt.GetSupportedFileTypes() { |
| 132 | + if ext == supportedExt { |
| 133 | + return parsedURL, ext, true |
| 134 | + } |
| 135 | + } |
| 136 | + return nil, "", false |
| 137 | +} |
| 138 | + |
| 139 | +func shouldReplaceFileURL(providerType string, parsedURL *url.URL) bool { |
| 140 | + if providerType != "OpenAI" && providerType != "Azure" { |
| 141 | + return true |
| 142 | + } |
| 143 | + return isLocalURL(parsedURL) |
| 144 | +} |
| 145 | + |
| 146 | +func isLocalURL(parsedURL *url.URL) bool { |
| 147 | + hostname := strings.ToLower(parsedURL.Hostname()) |
| 148 | + if hostname == "localhost" { |
| 149 | + return true |
| 150 | + } |
| 151 | + |
| 152 | + ip := net.ParseIP(hostname) |
| 153 | + if ip == nil { |
| 154 | + return false |
| 155 | + } |
| 156 | + return ip.IsLoopback() || ip.IsPrivate() |
| 157 | +} |
| 158 | + |
| 159 | +func getFileContent(rawURL string, ext string, lang string) (string, error) { |
| 160 | + if content, ok := fileContentCache.Load(rawURL); ok { |
| 161 | + return content.(string), nil |
| 162 | + } |
| 163 | + |
| 164 | + value, err, _ := fileContentGroup.Do(rawURL, func() (interface{}, error) { |
| 165 | + if content, ok := fileContentCache.Load(rawURL); ok { |
| 166 | + return content.(string), nil |
| 167 | + } |
| 168 | + |
| 169 | + content, err := txt.GetParsedTextFromUrl(rawURL, ext, lang) |
| 170 | + if err != nil { |
| 171 | + return "", err |
| 172 | + } |
| 173 | + fileContentCache.Store(rawURL, content) |
| 174 | + return content, nil |
| 175 | + }) |
| 176 | + if err != nil { |
| 177 | + return "", err |
| 178 | + } |
| 179 | + return value.(string), nil |
| 180 | +} |
0 commit comments