PyPI - khoj - Versions diffs - 1.23.1.dev1__py3-none-any.whl → 1.23.4.dev1__py3-none-any.whl - Mend

khoj 1.23.1.dev1py3-none-any.whl → 1.23.4.dev1py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (71) hide show

khoj/interface/email/task.html CHANGED Viewed

@@ -1,40 +1,37 @@
 <!DOCTYPE html>
-<html>
-    <head>
-        <title>Khoj AI - Automation</title>
-    </head>
-<body>
-<body style="font-family: 'Verdana', sans-serif; font-weight: 400; font-style: normal; padding: 0; text-align: left; width: 600px; margin: 20px auto;">
-<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1, user-scalable=no">
-<a class="logo" href="https://khoj.dev" target="_blank" style="text-decoration: none; text-decoration: underline dotted;">
-    <img src="https://khoj.dev/khoj-logo-sideways-500.png" alt="Khoj Logo" style="width: 100px;">
-</a>
-<div class="calls-to-action" style="margin-top: 20px;">
-    <div>
-        <h1 style="color: #333; font-size: large; font-weight: bold; margin: 0; line-height: 1.5; background-color: #fee285; padding: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.5);">Your Automation, From Your Personal AI (Preview)</h1>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Khoj AI - Automation</title>
+</head>
+<body style="font-family: 'Arial', sans-serif; line-height: 1.6; color: #333; max-width: 600px; margin: 0 auto; padding: 20px; background-color: #f5f5f5;">
+    <div style="background-color: #ffffff; border-radius: 10px; box-shadow: 0 0 20px rgba(0, 0, 0, 0.1); padding: 30px;">
+        <a href="https://khoj.dev" target="_blank" style="display: block; text-align: center; margin-bottom: 20px; text-decoration: none;">
+            <img src="https://assets.khoj.dev/khoj_logo.png" alt="Khoj Logo" style="width: 120px;">
+        </a>
-        <div style="display: grid; grid-template-columns: 1fr; grid-gap: 12px; margin-top: 20px;">
-            <div style="border: 1px solid black; border-radius: 8px; padding: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0); margin-top: 20px;">
-                <a href="https://app.khoj.dev/automations" style="text-decoration: none; text-decoration: underline dotted;">
-                    <h3 style="color: #333; font-size: large; margin: 0; padding: 0; line-height: 2.0; background-color: #b8f1c7; padding: 8px; ">{{subject}}</h3>
-                </a>
-                <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">{{result}}</p>
-            </div>
+        <h1 style="font-size: 24px; color: #2c3e50; margin-bottom: 20px; text-align: center; border-bottom: 2px solid #FFA07A; padding-bottom: 10px;">Your Automation, From Your Personal AI</h1>
+        <div style="background-color: #f8f9fa; border-left: 4px solid #FFA07A; padding: 15px; margin-bottom: 20px;">
+            <h3 style="color: #2c3e50; margin-top: 0;">{{ subject }}</h3>
+            <p style="margin-bottom: 0;">{{ result }}</p>
+        </div>
+        <div style="font-size: 14px; color: #666; margin-bottom: 20px;">
+            <p>The automation I ran on your behalf: {{ query }}</p>
+            <p>You can manage your automations via <a href="https://app.khoj.dev/automations" style="color: #007bff; text-decoration: none;">the settings page</a>.</p>
+            <p>This is an experimental feature. Please share any feedback with <a href="mailto:team@khoj.dev" style="color: #007bff; text-decoration: none;">team@khoj.dev</a>.</p>
         </div>
-        <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">The automation I ran on your behalf: {{query}}</p>
-        <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">You can manage your automations via <a href="https://app.khoj.dev/automations">the settings page</a>.</p>
-        <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">This is an experimental feature. Please share any feedback with <a href="mailto:team@khoj.dev">team@khoj.dev</a>.</p>
-    </div>
-</div>
-<p style="color: #333; font-size: large; margin-top: 20px; padding: 0; line-height: 1.5;">- Khoj</p>
-<table style="width: 100%; margin-top: 20px;">
-    <tr>
-        <td style="text-align: center;"><a href="https://docs.khoj.dev" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">Docs</a></td>
-        <td style="text-align: center;"><a href="https://github.com/khoj-ai/khoj" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">GitHub</a></td>
-        <td style="text-align: center;"><a href="https://twitter.com/khoj_ai" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">Twitter</a></td>
-        <td style="text-align: center;"><a href="https://www.linkedin.com/company/khoj-ai" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">LinkedIn</a></td>
-    </tr>
-</table>
+        <div style="font-size: 18px; font-weight: bold; margin-top: 30px; text-align: right;">- Khoj</div>
+        <div style="margin-top: 30px; text-align: center;">
+            <a href="https://docs.khoj.dev" target="_blank" style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #333; text-decoration: none; border-radius: 5px;">Docs</a>
+            <a href="https://github.com/khoj-ai/khoj" target="_blank" style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #333; text-decoration: none; border-radius: 5px;">GitHub</a>
+            <a href="https://twitter.com/khoj_ai" target="_blank" style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #333; text-decoration: none; border-radius: 5px;">Twitter</a>
+            <a href="https://www.linkedin.com/company/khoj-ai" target="_blank" style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #333; text-decoration: none; border-radius: 5px;">LinkedIn</a>
+        </div>
+    </div>
 </body>
 </html>

khoj/interface/email/welcome.html CHANGED Viewed

@@ -1,61 +1,90 @@
 <!DOCTYPE html>
-<html>
-    <head>
-        <title>Welcome to Khoj</title>
-    </head>
-<body>
-<body style="font-family: 'Verdana', sans-serif; font-weight: 400; font-style: normal; padding: 0; text-align: left; width: 600px; margin: 20px auto;">
-<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1, user-scalable=no">
-<a class="logo" href="https://khoj.dev" target="_blank" style="text-decoration: none; text-decoration: underline dotted;">
-    <img src="https://khoj.dev/khoj-logo-sideways-500.png" alt="Khoj Logo" style="width: 100px;">
-</a>
-<div class="calls-to-action" style="margin-top: 20px;">
-    <div>
-        <h1 style="color: #333; font-size: large; font-weight: bold; margin: 0; line-height: 1.5; background-color: #fee285; padding: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.5);">Merge AI with your brain</h1>
-        <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">Hi {{name}}! We are psyched to be part of your journey with personal AI. To better help you, we're committed to staying transparent, accessible, and completely open-source.</p>
-        <a class="button" href="https://app.khoj.dev" target="_blank" style="display: block; width: 200px; text-align: center; padding: 10px; margin-top: 20px; color: #333; background-color: #fee285; text-decoration: none; border-radius: 5px; font-weight: bold; transition: background-color 0.3s ease; box-shadow: 6px 6px rgba(0, 0, 0, 1.0); padding: 4px; font-size: large; text-transform: uppercase;">Get Started</a>
-        <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">You're about to get a whole lot more productive.</p>
-        <div style="display: grid; grid-template-columns: 1fr 1fr; grid-gap: 12px; margin-top: 20px;">
-            <div style="border: 1px solid black; border-radius: 8px; padding: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0); margin-top: 20px;">
-                <a href="https://docs.khoj.dev/features/online_search" style="text-decoration: none; text-decoration: underline dotted;">
-                    <h3 style="color: #333; font-size: large; margin: 0; padding: 0; line-height: 2.0; background-color: #b8f1c7; padding: 8px; ">Ditch the search bar</h3>
-                </a>
-                <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">You don't need to click around Google results and sift through information yourself, because Khoj is connected to the internet.</p>
-            </div>
-            <div style="border: 1px solid black; border-radius: 8px; padding: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0); margin-top: 20px;">
-                <a href="https://app.khoj.dev/agents" style="text-decoration: none; text-decoration: underline dotted;">
-                    <h3 style="color: #333; font-size: large; margin: 0; padding: 0; line-height: 2.0; background-color: #b8f1c7; padding: 8px;">Get a village, not just an agent</h3>
-                </a>
-                <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">Khoj can fill the need for more specialized assistance, <a href="https://blog.khoj.dev/posts/using-khoj-for-studying/">such as tutoring</a>, with its curated agents. You get a whole team, always available.</p>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Welcome to Khoj</title>
+</head>
+<body
+    style="font-family: 'Arial', sans-serif; line-height: 1.6; color: #333; max-width: 600px; margin: 0 auto; padding: 20px; background-color: #f5f5f5;">
+    <div
+        style="background-color: #ffffff; border-radius: 10px; box-shadow: 0 0 20px rgba(0, 0, 0, 0.1); padding: 30px;">
+        <a href="https://khoj.dev" target="_blank"
+            style="display: block; text-align: center; margin-bottom: 20px; text-decoration: none;">
+            <img src="https://assets.khoj.dev/khoj_logo.png" alt="Khoj Logo" style="width: 120px;">
+        </a>
+        <h1
+            style="font-size: 24px; color: #2c3e50; margin-bottom: 20px; text-align: center; border-bottom: 2px solid #FFA07A; padding-bottom: 10px;">
+            Merge AI with your brain</h1>
+        <p style="font-size: 16px; color: #333; margin-bottom: 20px;">Hi {{name}}! We are psyched to be part of your
+            journey with personal AI. To better help you, we're committed to staying transparent, accessible, and
+            completely open-source.</p>
+        <a href="https://app.khoj.dev" target="_blank"
+            style="display: block; width: 200px; text-align: center; padding: 10px; margin: 20px auto; background-color: #FFA07A; color: #ffffff; text-decoration: none; border-radius: 5px; font-weight: bold; font-size: 16px; text-transform: uppercase;">Get
+            Started</a>
+        <p style="font-size: 16px; color: #333; margin-bottom: 20px;">You're about to get a whole lot more productive.
+        </p>
+        <a href="https://docs.khoj.dev/features/online_search"
+            style="color: #FFA07A; text-decoration: none; font-weight: bold; font-size: 14px;">
+            <div style="display: grid; grid-template-columns: 1fr 1fr; grid-gap: 20px; margin-bottom: 20px;">
+                <div style="background-color: #f8f9fa; border-left: 4px solid #FFA07A; padding: 15px;">
+                    <h3 style="color: #2c3e50; margin-top: 0; font-size: 18px;">Ditch the search bar</h3>
+                    <p style="font-size: 14px; color: #666; margin-bottom: 0;">You don't need to click around Google
+                        results
+                        and sift through information yourself, because Khoj is connected to the internet.</p>
+                </div>
+        </a>
+        <a href="https://app.khoj.dev/agents"
+            style="color: #FFA07A; text-decoration: none; font-weight: bold; font-size: 14px;">
+            <div style="background-color: #f8f9fa; border-left: 4px solid #FFA07A; padding: 15px;">
+                <h3 style="color: #2c3e50; margin-top: 0; font-size: 18px;">Get a village, not just an agent</h3>
+                <p style="font-size: 14px; color: #666; margin-bottom: 0;">Khoj can fill the need for more specialized
+                    assistance, such as tutoring, with its curated agents. You get a whole team, always available.</p>
             </div>
-            <div style="border: 1px solid black; border-radius: 8px; padding: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0); margin-top: 20px;">
-                <a href="https://docs.khoj.dev/category/clients" style="text-decoration: none; text-decoration: underline dotted;">
-                    <h3 style="color: #333; font-size: large; margin: 0; padding: 0; line-height: 2.0; background-color: #b8f1c7; padding: 8px;">Available where you are</h3>
-                </a>
-                <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">Build on top of your digital brain. Khoj stores whatever data you share with it, so you can get answers from your personal notes and documents in your native language. You can engage from your desktop, Obsidian, WhatsApp, or the web.</p>
+        </a>
+        <a href="https://docs.khoj.dev/category/clients"
+            style="color: #FFA07A; text-decoration: none; font-weight: bold; font-size: 14px;">
+            <div style="background-color: #f8f9fa; border-left: 4px solid #FFA07A; padding: 15px;">
+                <h3 style="color: #2c3e50; margin-top: 0; font-size: 18px;">Activate your data</h3>
+                <p style="font-size: 14px; color: #666; margin-bottom: 0;">Build on top of your digital brain. Khoj
+                    stores whatever data you share with it, so you can get answers from your personal notes and
+                    documents in your native language.</p>
             </div>
-            <div style="border: 1px solid black; border-radius: 8px; padding: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0); margin-top: 20px;">
-                <a href="https://blog.khoj.dev/posts/how-khoj-generates-images/" style="text-decoration: none; text-decoration: underline dotted;">
-                    <h3 style="color: #333; font-size: large; margin: 0; padding: 0; line-height: 2.0; background-color: #b8f1c7; padding: 8px;">Create rich, contextual images</h3>
-                </a>
-                <p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">With your shared data, Khoj can help you create astoundingly personal images depicting scenes of what's important to you.</p>
+        </a>
+        <a href="https://blog.khoj.dev/posts/how-khoj-generates-images/"
+            style="color: #FFA07A; text-decoration: none; font-weight: bold; font-size: 14px;">
+            <div style="background-color: #f8f9fa; border-left: 4px solid #FFA07A; padding: 15px;">
+                <h3 style="color: #2c3e50; margin-top: 0; font-size: 18px;">Create rich, contextual images</h3>
+                <p style="font-size: 14px; color: #666; margin-bottom: 0;">With your shared data, Khoj can help you
+                    create astoundingly personal images depicting scenes of what's important to you.</p>
             </div>
-        </div>
+        </a>
     </div>
-</div>
-<p style="color: #333; font-size: medium; margin-top: 20px; padding: 0; line-height: 1.5;">Like something? Dislike something? Searching for some other magical feature? Our inbox is always open for feedback! Reply to this email and say hi to introduce yourself 👋🏽.</p>
-<p style="color: #333; font-size: large; margin-top: 20px; padding: 0; line-height: 1.5;">- The Khoj Team</p>
-<table style="width: 100%; margin-top: 20px;">
-    <tr>
-        <td style="text-align: center;"><a href="https://docs.khoj.dev" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">Docs</a></td>
-        <td style="text-align: center;"><a href="https://github.com/khoj-ai/khoj" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">GitHub</a></td>
-        <td style="text-align: center;"><a href="https://twitter.com/khoj_ai" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">Twitter</a></td>
-        <td style="text-align: center;"><a href="https://www.linkedin.com/company/khoj-ai" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">LinkedIn</a></td>
-        <td style="text-align: center;"><a href="https://discord.gg/BDgyabRM6e" target="_blank" style="padding: 8px; color: #333; background-color: #fee285; border-radius: 8px; box-shadow: 6px 6px rgba(0, 0, 0, 1.0);">Discord</a></td>
-    </tr>
-</table>
+    <p style="font-size: 16px; color: #333; margin-bottom: 20px;">Like something? Dislike something? Searching for
+        some other magical feature? Our inbox is always open for feedback! Reply to this email and say hi to
+        introduce yourself 👋🏽.</p>
+    <div style="font-size: 18px; font-weight: bold; margin-top: 30px; text-align: right;">- The Khoj Team</div>
+    <div style="margin-top: 30px; text-align: center;">
+        <a href="https://docs.khoj.dev" target="_blank"
+            style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #ffffff; text-decoration: none; border-radius: 5px;">Docs</a>
+        <a href="https://github.com/khoj-ai/khoj" target="_blank"
+            style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #ffffff; text-decoration: none; border-radius: 5px;">GitHub</a>
+        <a href="https://twitter.com/khoj_ai" target="_blank"
+            style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #ffffff; text-decoration: none; border-radius: 5px;">Twitter</a>
+        <a href="https://www.linkedin.com/company/khoj-ai" target="_blank"
+            style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #ffffff; text-decoration: none; border-radius: 5px;">LinkedIn</a>
+        <a href="https://discord.gg/BDgyabRM6e" target="_blank"
+            style="display: inline-block; margin: 0 10px; padding: 8px 15px; background-color: #FFA07A; color: #ffffff; text-decoration: none; border-radius: 5px;">Discord</a>
+    </div>
+    </div>
 </body>
 </html>

khoj/main.py CHANGED Viewed

@@ -131,7 +131,7 @@ def run(should_start_server=True):
     logger.info(f"📦 Initializing DB:\n{db_migrate_output.getvalue().strip()}")
     logger.debug(f"🌍 Initializing Web Client:\n{collectstatic_output.getvalue().strip()}")
-    initialization()
+    initialization(not args.non_interactive)
     # Create app directory, if it doesn't exist
     state.config_file.parent.mkdir(parents=True, exist_ok=True)

khoj/processor/content/images/image_to_entries.py CHANGED Viewed

@@ -4,8 +4,6 @@ import os
 from datetime import datetime
 from typing import Dict, List, Tuple
-from rapidocr_onnxruntime import RapidOCR
 from khoj.database.models import Entry as DbEntry
 from khoj.database.models import KhojUser
 from khoj.processor.content.text_to_entries import TextToEntries
@@ -58,7 +56,6 @@ class ImageToEntries(TextToEntries):
         entry_to_location_map: List[Tuple[str, str]] = []
         for image_file in image_files:
             try:
-                loader = RapidOCR()
                 bytes = image_files[image_file]
                 # write the image to a temporary file
                 timestamp_now = datetime.utcnow().timestamp()
@@ -71,13 +68,18 @@ class ImageToEntries(TextToEntries):
                     bytes = image_files[image_file]
                     f.write(bytes)
                 try:
+                    from rapidocr_onnxruntime import RapidOCR
+                    loader = RapidOCR()
                     image_entries_per_file = ""
                     result, _ = loader(tmp_file)
                     if result:
                         expanded_entries = [text[1] for text in result]
                         image_entries_per_file = " ".join(expanded_entries)
                 except ImportError:
-                    logger.warning(f"Unable to process file: {image_file}. This file will not be indexed.")
+                    logger.warning(
+                        f"Unable to process image or scanned file for text: {image_file}. This file will not be indexed."
+                    )
                     continue
                 entry_to_location_map.append((image_entries_per_file, image_file))
                 entries.extend([image_entries_per_file])

khoj/processor/conversation/google/utils.py CHANGED Viewed

@@ -1,7 +1,18 @@
 import logging
+import random
 from threading import Thread
 import google.generativeai as genai
+from google.generativeai.types.answer_types import FinishReason
+from google.generativeai.types.generation_types import (
+    GenerateContentResponse,
+    StopCandidateException,
+)
+from google.generativeai.types.safety_types import (
+    HarmBlockThreshold,
+    HarmCategory,
+    HarmProbability,
+)
 from tenacity import (
     before_sleep_log,
     retry,
@@ -32,14 +43,35 @@ def gemini_completion_with_backoff(
     model_kwargs = model_kwargs or dict()
     model_kwargs["temperature"] = temperature
     model_kwargs["max_output_tokens"] = max_tokens
-    model = genai.GenerativeModel(model_name, generation_config=model_kwargs, system_instruction=system_prompt)
+    model = genai.GenerativeModel(
+        model_name,
+        generation_config=model_kwargs,
+        system_instruction=system_prompt,
+        safety_settings={
+            HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+            HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+            HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+            HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+        },
+    )
     formatted_messages = [{"role": message.role, "parts": [message.content]} for message in messages]
-    # all messages up to the last are considered to be part of the chat history
+    # Start chat session. All messages up to the last are considered to be part of the chat history
     chat_session = model.start_chat(history=formatted_messages[0:-1])
-    # the last message is considered to be the current prompt
-    aggregated_response = chat_session.send_message(formatted_messages[-1]["parts"][0])
-    return aggregated_response.text
+    try:
+        # Generate the response. The last message is considered to be the current prompt
+        aggregated_response = chat_session.send_message(formatted_messages[-1]["parts"][0])
+        return aggregated_response.text
+    except StopCandidateException as e:
+        response_message, _ = handle_gemini_response(e.args)
+        # Respond with reason for stopping
+        logger.warning(
+            f"LLM Response Prevented for {model_name}: {response_message}.\n"
+            + f"Last Message by {messages[-1].role}: {messages[-1].content}"
+        )
+        return response_message
 @retry(
@@ -79,15 +111,82 @@ def gemini_llm_thread(
         model_kwargs["temperature"] = temperature
         model_kwargs["max_output_tokens"] = max_tokens
         model_kwargs["stop_sequences"] = ["Notes:\n["]
-        model = genai.GenerativeModel(model_name, generation_config=model_kwargs, system_instruction=system_prompt)
+        model = genai.GenerativeModel(
+            model_name,
+            generation_config=model_kwargs,
+            system_instruction=system_prompt,
+            safety_settings={
+                HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+                HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+                HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+                HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
+            },
+        )
         formatted_messages = [{"role": message.role, "parts": [message.content]} for message in messages]
         # all messages up to the last are considered to be part of the chat history
         chat_session = model.start_chat(history=formatted_messages[0:-1])
         # the last message is considered to be the current prompt
         for chunk in chat_session.send_message(formatted_messages[-1]["parts"][0], stream=True):
-            g.send(chunk.text)
+            message, stopped = handle_gemini_response(chunk.candidates, chunk.prompt_feedback)
+            message = message or chunk.text
+            g.send(message)
+            if stopped:
+                raise StopCandidateException(message)
+    except StopCandidateException as e:
+        logger.warning(
+            f"LLM Response Prevented for {model_name}: {e.args[0]}.\n"
+            + f"Last Message by {messages[-1].role}: {messages[-1].content}"
+        )
     except Exception as e:
         logger.error(f"Error in gemini_llm_thread: {e}", exc_info=True)
     finally:
         g.close()
+def handle_gemini_response(candidates, prompt_feedback=None):
+    """Check if Gemini response was blocked and return an explanatory error message."""
+    # Check if the response was blocked due to safety concerns with the prompt
+    if len(candidates) == 0 and prompt_feedback:
+        message = f"\nI'd prefer to not respond to that due to **{prompt_feedback.block_reason.name}** issues with your query."
+        stopped = True
+    # Check if the response was blocked due to safety concerns with the generated content
+    elif candidates[0].finish_reason == FinishReason.SAFETY:
+        message = generate_safety_response(candidates[0].safety_ratings)
+        stopped = True
+    # Check if the response was stopped due to reaching maximum token limit or other reasons
+    elif candidates[0].finish_reason != FinishReason.STOP:
+        message = f"\nI can't talk further about that because of **{candidates[0].finish_reason.name} issue.**"
+        stopped = True
+    # Otherwise, the response is valid and can be used
+    else:
+        message = None
+        stopped = False
+    return message, stopped
+def generate_safety_response(safety_ratings):
+    """Generate a conversational response based on the safety ratings of the response."""
+    # Get the safety rating with the highest probability
+    max_safety_rating = sorted(safety_ratings, key=lambda x: x.probability, reverse=True)[0]
+    # Remove the "HARM_CATEGORY_" prefix and title case the category name
+    max_safety_category = " ".join(max_safety_rating.category.name.split("_")[2:]).title()
+    # Add a bit of variety to the discomfort level based on the safety rating probability
+    discomfort_level = {
+        HarmProbability.HARM_PROBABILITY_UNSPECIFIED: " ",
+        HarmProbability.LOW: "a bit ",
+        HarmProbability.MEDIUM: "moderately ",
+        HarmProbability.HIGH: random.choice(["very ", "quite ", "fairly "]),
+    }[max_safety_rating.probability]
+    # Generate a response using a random response template
+    safety_response_choice = random.choice(
+        [
+            "\nUmm, I'd rather not to respond to that. The conversation has some probability of going into **{category}** territory.",
+            "\nI'd prefer not to talk about **{category}** related topics. It makes me {discomfort_level}uncomfortable.",
+            "\nI feel {discomfort_level}squeamish talking about **{category}** related stuff! Can we talk about something less controversial?",
+            "\nThat sounds {discomfort_level}outside the [Overtone Window](https://en.wikipedia.org/wiki/Overton_window) of acceptable conversation. Should we stick to something less {category} related?",
+        ]
+    )
+    return safety_response_choice.format(
+        category=max_safety_category, probability=max_safety_rating.probability.name, discomfort_level=discomfort_level
+    )

khoj/processor/conversation/utils.py CHANGED Viewed

@@ -18,13 +18,20 @@ from khoj.utils.helpers import is_none_or_empty, merge_dicts
 logger = logging.getLogger(__name__)
 model_to_prompt_size = {
+    # OpenAI Models
     "gpt-3.5-turbo": 12000,
-    "gpt-3.5-turbo-0125": 12000,
-    "gpt-4-0125-preview": 20000,
     "gpt-4-turbo-preview": 20000,
+    "gpt-4o": 20000,
     "gpt-4o-mini": 20000,
     "o1-preview": 20000,
     "o1-mini": 20000,
+    # Google Models
+    "gemini-1.5-flash": 20000,
+    "gemini-1.5-pro": 20000,
+    # Anthropic Models
+    "claude-3-5-sonnet-20240620": 20000,
+    "claude-3-opus-20240229": 20000,
+    # Offline Models
     "TheBloke/Mistral-7B-Instruct-v0.2-GGUF": 3500,
     "NousResearch/Hermes-2-Pro-Mistral-7B-GGUF": 3500,
     "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF": 20000,
@@ -100,7 +107,7 @@ def save_to_conversation_log(
     inferred_queries: List[str] = [],
     intent_type: str = "remember",
     client_application: ClientApplication = None,
-    conversation_id: int = None,
+    conversation_id: str = None,
     automation_id: str = None,
     uploaded_image_url: str = None,
 ):
@@ -163,7 +170,7 @@ def generate_chatml_messages_with_context(
         if loaded_model:
             max_prompt_size = infer_max_tokens(loaded_model.n_ctx(), model_to_prompt_size.get(model_name, math.inf))
         else:
-            max_prompt_size = model_to_prompt_size.get(model_name, 2000)
+            max_prompt_size = model_to_prompt_size.get(model_name, 10000)
     # Scale lookback turns proportional to max prompt size supported by model
     lookback_turns = max_prompt_size // 750
@@ -291,8 +298,6 @@ def reciprocal_conversation_to_chatml(message_pair):
     return [ChatMessage(content=message, role=role) for message, role in zip(message_pair, ["user", "assistant"])]
-def remove_json_codeblock(response):
+def remove_json_codeblock(response: str):
     """Remove any markdown json codeblock formatting if present. Useful for non schema enforceable models"""
-    if response.startswith("```json") and response.endswith("```"):
-        response = response[7:-3]
-    return response
+    return response.removeprefix("```json").removesuffix("```")

khoj/routers/api.py CHANGED Viewed

@@ -328,7 +328,7 @@ async def extract_references_and_questions(
     q: str,
     n: int,
     d: float,
-    conversation_id: int,
+    conversation_id: str,
     conversation_commands: List[ConversationCommand] = [ConversationCommand.Default],
     location_data: LocationData = None,
     send_status_func: Optional[Callable] = None,

khoj/routers/api_chat.py CHANGED Viewed

@@ -77,9 +77,7 @@ from khoj.routers.email import send_query_feedback
 @api_chat.get("/conversation/file-filters/{conversation_id}", response_class=Response)
 @requires(["authenticated"])
 def get_file_filter(request: Request, conversation_id: str) -> Response:
-    conversation = ConversationAdapters.get_conversation_by_user(
-        request.user.object, conversation_id=int(conversation_id)
-    )
+    conversation = ConversationAdapters.get_conversation_by_user(request.user.object, conversation_id=conversation_id)
     if not conversation:
         return Response(content=json.dumps({"status": "error", "message": "Conversation not found"}), status_code=404)
@@ -95,7 +93,7 @@ def get_file_filter(request: Request, conversation_id: str) -> Response:
 @api_chat.delete("/conversation/file-filters/bulk", response_class=Response)
 @requires(["authenticated"])
 def remove_files_filter(request: Request, filter: FilesFilterRequest) -> Response:
-    conversation_id = int(filter.conversation_id)
+    conversation_id = filter.conversation_id
     files_filter = filter.filenames
     file_filters = ConversationAdapters.remove_files_from_filter(request.user.object, conversation_id, files_filter)
     return Response(content=json.dumps(file_filters), media_type="application/json", status_code=200)
@@ -105,7 +103,7 @@ def remove_files_filter(request: Request, filter: FilesFilterRequest) -> Respons
 @requires(["authenticated"])
 def add_files_filter(request: Request, filter: FilesFilterRequest):
     try:
-        conversation_id = int(filter.conversation_id)
+        conversation_id = filter.conversation_id
         files_filter = filter.filenames
         file_filters = ConversationAdapters.add_files_to_filter(request.user.object, conversation_id, files_filter)
         return Response(content=json.dumps(file_filters), media_type="application/json", status_code=200)
@@ -118,7 +116,7 @@ def add_files_filter(request: Request, filter: FilesFilterRequest):
 @requires(["authenticated"])
 def add_file_filter(request: Request, filter: FileFilterRequest):
     try:
-        conversation_id = int(filter.conversation_id)
+        conversation_id = filter.conversation_id
         files_filter = [filter.filename]
         file_filters = ConversationAdapters.add_files_to_filter(request.user.object, conversation_id, files_filter)
         return Response(content=json.dumps(file_filters), media_type="application/json", status_code=200)
@@ -130,7 +128,7 @@ def add_file_filter(request: Request, filter: FileFilterRequest):
 @api_chat.delete("/conversation/file-filters", response_class=Response)
 @requires(["authenticated"])
 def remove_file_filter(request: Request, filter: FileFilterRequest) -> Response:
-    conversation_id = int(filter.conversation_id)
+    conversation_id = filter.conversation_id
     files_filter = [filter.filename]
     file_filters = ConversationAdapters.remove_files_from_filter(request.user.object, conversation_id, files_filter)
     return Response(content=json.dumps(file_filters), media_type="application/json", status_code=200)
@@ -189,7 +187,7 @@ async def chat_starters(
 def chat_history(
     request: Request,
     common: CommonQueryParams,
-    conversation_id: Optional[int] = None,
+    conversation_id: Optional[str] = None,
     n: Optional[int] = None,
 ):
     user = request.user.object
@@ -312,7 +310,7 @@ def get_shared_chat(
 async def clear_chat_history(
     request: Request,
     common: CommonQueryParams,
-    conversation_id: Optional[int] = None,
+    conversation_id: Optional[str] = None,
 ):
     user = request.user.object
@@ -375,7 +373,7 @@ def fork_public_conversation(
 def duplicate_chat_history_public_conversation(
     request: Request,
     common: CommonQueryParams,
-    conversation_id: int,
+    conversation_id: str,
 ):
     user = request.user.object
     domain = request.headers.get("host")
@@ -423,7 +421,7 @@ def chat_sessions(
     session_values = [
         {
-            "conversation_id": session[0],
+            "conversation_id": str(session[0]),
             "slug": session[2] or session[1],
             "agent_name": session[4],
             "agent_avatar": session[5],
@@ -455,7 +453,7 @@ async def create_chat_session(
     # Create new Conversation Session
     conversation = await ConversationAdapters.acreate_conversation_session(user, request.user.client_app, agent_slug)
-    response = {"conversation_id": conversation.id}
+    response = {"conversation_id": str(conversation.id)}
     conversation_metadata = {
         "agent": agent_slug,
@@ -497,7 +495,7 @@ async def set_conversation_title(
     request: Request,
     common: CommonQueryParams,
     title: str,
-    conversation_id: Optional[int] = None,
+    conversation_id: Optional[str] = None,
 ) -> Response:
     user = request.user.object
     title = title.strip()[:200]
@@ -527,7 +525,7 @@ class ChatRequestBody(BaseModel):
     d: Optional[float] = None
     stream: Optional[bool] = False
     title: Optional[str] = None
-    conversation_id: Optional[int] = None
+    conversation_id: Optional[str] = None
     city: Optional[str] = None
     region: Optional[str] = None
     country: Optional[str] = None
@@ -1016,7 +1014,7 @@ async def get_chat(
     d: float = None,
     stream: Optional[bool] = False,
     title: Optional[str] = None,
-    conversation_id: Optional[int] = None,
+    conversation_id: Optional[str] = None,
     city: Optional[str] = None,
     region: Optional[str] = None,
     country: Optional[str] = None,

khoj 1.23.1.dev1__py3-none-any.whl → 1.23.4.dev1__py3-none-any.whl

khoj 1.23.1.dev1py3-none-any.whl → 1.23.4.dev1py3-none-any.whl