Add additional telemetry for system understanding (#316)

* Add additional telemetry in order to understand which data sources are the most useful
* Make actions side by side in the configuration page
* Restore main run command
* Update links to point to wiki pages for Github, Notion integrations
* Stanardize nomenclature of the api_type to use _config suffix

Remove header fields that aren't actually helpful for understanding config usage

src/khoj/interface/web/base_config.html

@@ -51,6 +51,10 @@
             body.khoj-configure {
                 padding: 0;
             }
+
+            div.section {
+                padding: 12px;
+            }
         }
 
         img.khoj-logo {
@@ -69,6 +73,11 @@
             display: grid;
             justify-self: center;
         }
+
+        div.instructions {
+            font-size: large;
+        }
+
         .section-title {
             margin: 0;
             padding: 0 0 16px 0;
@@ -162,6 +171,11 @@
             max-width: 16px;
         }
 
+        div.finalize-actions {
+            grid-auto-flow: column;
+            grid-gap: 24px;
+        }
+
         @media screen and (max-width: 600px) {
             .section-cards {
                 grid-template-columns: 1fr;

src/khoj/interface/web/config.html

@@ -204,6 +204,8 @@
             <input type="range" id="results-count-slider" name="results-count-slider" min="1" max="10" step="1" value="5">
         </div>
         <div id="status" style="display: none;"></div>
+    </div>
+    <div class="section finalize-actions">
         <button id="configure" type="submit" title="Update index with the latest changes">⚙️ Configure</button>
         <button id="reinitialize" type="submit" title="Regenerate index from scratch">🔄 Reinitialize</button>
     </div>

src/khoj/interface/web/content_type_github_input.html

@@ -5,6 +5,9 @@
         <h2 class="section-title">
             <img class="card-icon" src="/static/assets/icons/github.svg" alt="Github">
             <span class="card-title-text">Github</span>
+            <div class="instructions">
+                <a href="https://github.com/khoj-ai/khoj/wiki/Setup-Github-integration">ⓘ Help</a>
+            </div>
         </h2>
         <form>
             <table>

src/khoj/interface/web/content_type_notion_input.html

@@ -5,6 +5,9 @@
         <h2 class="section-title">
             <img class="card-icon" src="/static/assets/icons/notion.svg" alt="Notion">
             <span class="card-title-text">Notion</span>
+            <div class="instructions">
+                <a href="https://github.com/khoj-ai/khoj/wiki/Setup-Notion-Integration">ⓘ Help</a>
+            </div>
         </h2>
         <form>
             <table>

src/khoj/routers/api.py

@@ -34,7 +34,7 @@ from khoj.utils.state import SearchType
 from khoj.utils import state, constants
 from khoj.utils.yaml import save_config_to_file_updated_state
 from fastapi.responses import StreamingResponse, Response
-from khoj.routers.helpers import perform_chat_checks, generate_chat_response
+from khoj.routers.helpers import perform_chat_checks, generate_chat_response, update_telemetry_state
 from khoj.processor.conversation.gpt import extract_questions
 from fastapi.requests import Request
 
@@ -56,15 +56,44 @@ if not state.demo:
         return state.config
 
     @api.post("/config/data")
-    async def set_config_data(updated_config: FullConfig):
+    async def set_config_data(
+        request: Request,
+        updated_config: FullConfig,
+        client: Optional[str] = None,
+    ):
         state.config = updated_config
         with open(state.config_file, "w") as outfile:
             yaml.dump(yaml.safe_load(state.config.json(by_alias=True)), outfile)
             outfile.close()
+
+        configuration_update_metadata = dict()
+
+        if state.config.content_type is not None:
+            configuration_update_metadata["github"] = state.config.content_type.github is not None
+            configuration_update_metadata["notion"] = state.config.content_type.notion is not None
+            configuration_update_metadata["org"] = state.config.content_type.org is not None
+            configuration_update_metadata["pdf"] = state.config.content_type.pdf is not None
+            configuration_update_metadata["markdown"] = state.config.content_type.markdown is not None
+            configuration_update_metadata["plugins"] = state.config.content_type.plugins is not None
+
+        if state.config.processor is not None:
+            configuration_update_metadata["conversation_processor"] = state.config.processor.conversation is not None
+
+        update_telemetry_state(
+            request=request,
+            telemetry_type="api",
+            api="set_config",
+            client=client,
+            metadata=configuration_update_metadata,
+        )
         return state.config
 
     @api.post("/config/data/content_type/github", status_code=200)
-    async def set_content_config_github_data(updated_config: Union[GithubContentConfig, None]):
+    async def set_content_config_github_data(
+        request: Request,
+        updated_config: Union[GithubContentConfig, None],
+        client: Optional[str] = None,
+    ):
         _initialize_config()
 
         if not state.config.content_type:
@@ -72,6 +101,14 @@ if not state.demo:
         else:
             state.config.content_type.github = updated_config
 
+        update_telemetry_state(
+            request=request,
+            telemetry_type="api",
+            api="set_content_config",
+            client=client,
+            metadata={"content_type": "github"},
+        )
+
         try:
             save_config_to_file_updated_state()
             return {"status": "ok"}
@@ -79,7 +116,11 @@ if not state.demo:
             return {"status": "error", "message": str(e)}
 
     @api.post("/config/data/content_type/notion", status_code=200)
-    async def set_content_config_notion_data(updated_config: Union[NotionContentConfig, None]):
+    async def set_content_config_notion_data(
+        request: Request,
+        updated_config: Union[NotionContentConfig, None],
+        client: Optional[str] = None,
+    ):
         _initialize_config()
 
         if not state.config.content_type:
@@ -87,6 +128,14 @@ if not state.demo:
         else:
             state.config.content_type.notion = updated_config
 
+        update_telemetry_state(
+            request=request,
+            telemetry_type="api",
+            api="set_content_config",
+            client=client,
+            metadata={"content_type": "notion"},
+        )
+
         try:
             save_config_to_file_updated_state()
             return {"status": "ok"}
@@ -94,10 +143,22 @@ if not state.demo:
             return {"status": "error", "message": str(e)}
 
     @api.post("/delete/config/data/content_type/{content_type}", status_code=200)
-    async def remove_content_config_data(content_type: str):
+    async def remove_content_config_data(
+        request: Request,
+        content_type: str,
+        client: Optional[str] = None,
+    ):
         if not state.config or not state.config.content_type:
             return {"status": "ok"}
 
+        update_telemetry_state(
+            request=request,
+            telemetry_type="api",
+            api="delete_content_config",
+            client=client,
+            metadata={"content_type": content_type},
+        )
+
         if state.config.content_type:
             state.config.content_type[content_type] = None
 
@@ -121,12 +182,23 @@ if not state.demo:
             return {"status": "error", "message": str(e)}
 
     @api.post("/delete/config/data/processor/conversation", status_code=200)
-    async def remove_processor_conversation_config_data():
+    async def remove_processor_conversation_config_data(
+        request: Request,
+        client: Optional[str] = None,
+    ):
         if not state.config or not state.config.processor or not state.config.processor.conversation:
             return {"status": "ok"}
 
         state.config.processor.conversation = None
 
+        update_telemetry_state(
+            request=request,
+            telemetry_type="api",
+            api="delete_processor_config",
+            client=client,
+            metadata={"processor_type": "conversation"},
+        )
+
         try:
             save_config_to_file_updated_state()
             return {"status": "ok"}
@@ -134,7 +206,12 @@ if not state.demo:
             return {"status": "error", "message": str(e)}
 
     @api.post("/config/data/content_type/{content_type}", status_code=200)
-    async def set_content_config_data(content_type: str, updated_config: Union[TextContentConfig, None]):
+    async def set_content_config_data(
+        request: Request,
+        content_type: str,
+        updated_config: Union[TextContentConfig, None],
+        client: Optional[str] = None,
+    ):
         _initialize_config()
 
         if not state.config.content_type:
@@ -142,6 +219,14 @@ if not state.demo:
         else:
             state.config.content_type[content_type] = updated_config
 
+        update_telemetry_state(
+            request=request,
+            telemetry_type="api",
+            api="set_content_config",
+            client=client,
+            metadata={"content_type": content_type},
+        )
+
         try:
             save_config_to_file_updated_state()
             return {"status": "ok"}
@@ -149,11 +234,24 @@ if not state.demo:
             return {"status": "error", "message": str(e)}
 
     @api.post("/config/data/processor/conversation", status_code=200)
-    async def set_processor_conversation_config_data(updated_config: Union[ConversationProcessorConfig, None]):
+    async def set_processor_conversation_config_data(
+        request: Request,
+        updated_config: Union[ConversationProcessorConfig, None],
+        client: Optional[str] = None,
+    ):
         _initialize_config()
 
         state.config.processor = ProcessorConfig(conversation=updated_config)
         state.processor_config = configure_processor(state.config.processor)
+
+        update_telemetry_state(
+            request=request,
+            telemetry_type="api",
+            api="set_content_config",
+            client=client,
+            metadata={"processor_type": "conversation"},
+        )
+
         try:
             save_config_to_file_updated_state()
             return {"status": "ok"}
@@ -369,20 +467,16 @@ async def search(
     # Cache results
     state.query_cache[query_cache_key] = results
 
-    user_state = {
+    update_telemetry_state(
-        "client_host": request.client.host if request.client else "unknown",
+        request=request,
-        "user_agent": user_agent or "unknown",
+        telemetry_type="api",
-        "referer": referer or "unknown",
+        api="search",
-        "host": host or "unknown",
+        client=client,
-    }
+        user_agent=user_agent,
+        referer=referer,
+        host=host,
+    )
 
-    # Only log telemetry if query is new and not a continuation of previous query
-    if state.previous_query is None or state.previous_query not in user_query:
-        state.telemetry += [
-            log_telemetry(
-                telemetry_type="api", api="search", client=client, app_config=state.config.app, properties=user_state
-            )
-        ]
     state.previous_query = user_query
 
     end_time = time.time()
@@ -425,18 +519,15 @@ def update(
     else:
         logger.info("📬 Processor reconfigured via API")
 
-    user_state = {
+    update_telemetry_state(
-        "client_host": request.client.host if request.client else None,
+        request=request,
-        "user_agent": user_agent or "unknown",
+        telemetry_type="api",
-        "referer": referer or "unknown",
+        api="update",
-        "host": host or "unknown",
+        client=client,
-    }
+        user_agent=user_agent,
-
+        referer=referer,
-    state.telemetry += [
+        host=host,
-        log_telemetry(
+    )
-            telemetry_type="api", api="update", client=client, app_config=state.config.app, properties=user_state
-        )
-    ]
 
     return {"status": "ok", "message": "khoj reloaded"}
 
@@ -454,18 +545,15 @@ def chat_history(
     # Load Conversation History
     meta_log = state.processor_config.conversation.meta_log
 
-    user_state = {
+    update_telemetry_state(
-        "client_host": request.client.host if request.client else None,
+        request=request,
-        "user_agent": user_agent or "unknown",
+        telemetry_type="api",
-        "referer": referer or "unknown",
+        api="chat",
-        "host": host or "unknown",
+        client=client,
-    }
+        user_agent=user_agent,
-
+        referer=referer,
-    state.telemetry += [
+        host=host,
-        log_telemetry(
+    )
-            telemetry_type="api", api="chat", client=client, app_config=state.config.app, properties=user_state
-        )
-    ]
 
     return {"status": "ok", "response": meta_log.get("chat", [])}
 
@@ -509,18 +597,15 @@ async def chat(
 
     response_obj = {"response": actual_response, "context": compiled_references}
 
-    user_state = {
+    update_telemetry_state(
-        "client_host": request.client.host if request.client else None,
+        request=request,
-        "user_agent": user_agent or "unknown",
+        telemetry_type="api",
-        "referer": referer or "unknown",
+        api="chat",
-        "host": host or "unknown",
+        client=client,
-    }
+        user_agent=user_agent,
-
+        referer=referer,
-    state.telemetry += [
+        host=host,
-        log_telemetry(
+    )
-            telemetry_type="api", api="chat", client=client, app_config=state.config.app, properties=user_state
-        )
-    ]
 
     return Response(content=json.dumps(response_obj), media_type="application/json", status_code=200)
 

src/khoj/routers/helpers.py

@@ -1,11 +1,12 @@
-from fastapi import HTTPException
 import logging
 from datetime import datetime
 from functools import partial
-from typing import List
+from typing import List, Optional
+
+from fastapi import HTTPException, Request
 
 from khoj.utils import state
-from khoj.utils.helpers import timer
+from khoj.utils.helpers import timer, log_telemetry
 from khoj.processor.conversation.gpt import converse
 from khoj.processor.conversation.utils import message_to_log, reciprocal_conversation_to_chatml
 
@@ -24,6 +25,33 @@ def perform_chat_checks():
         )
 
 
+def update_telemetry_state(
+    request: Request,
+    telemetry_type: str,
+    api: str,
+    client: Optional[str] = None,
+    user_agent: Optional[str] = None,
+    referer: Optional[str] = None,
+    host: Optional[str] = None,
+    metadata: Optional[dict] = None,
+):
+    user_state = {
+        "client_host": request.client.host if request.client else None,
+        "user_agent": user_agent or "unknown",
+        "referer": referer or "unknown",
+        "host": host or "unknown",
+    }
+
+    if metadata:
+        user_state.update(metadata)
+
+    state.telemetry += [
+        log_telemetry(
+            telemetry_type=telemetry_type, api=api, client=client, app_config=state.config.app, properties=user_state
+        )
+    ]
+
+
 def generate_chat_response(
     q: str,
     meta_log: dict,