Feat: add token comsumption & speed to little lamp. (#6077)

### What problem does this PR solve?

#6059

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

agent/component/base.py

@@ -484,7 +484,7 @@ class ComponentBase(ABC):
                     if q["component_id"].lower().find("answer") == 0:
                         txt = []
                         for r, c in self._canvas.history[::-1][:self._param.message_history_window_size][::-1]:
-                            txt.append(f"{r.upper()}: {c}")
+                            txt.append(f"{r.upper()}:{c}")
                         txt = "\n".join(txt)
                         self._param.inputs.append({"content": txt, "component_id": q["component_id"]})
                         outs.append(pd.DataFrame([{"content": txt}]))
@@ -521,7 +521,7 @@ class ComponentBase(ABC):
             if u.lower().find("answer") >= 0:
                 for r, c in self._canvas.history[::-1]:
                     if r == "user":
-                        upstream_outs.append(pd.DataFrame([{"content": c, "component_id": u}]))
+                        upstream_outs.append(pd.DataFrame([{"content": f"USER:{c}", "component_id": u}]))
                         break
                 break
             if self.component_name.lower().find("answer") >= 0 and self.get_component_name(u) in ["relevant"]:

api/db/services/dialog_service.py

@@ -304,8 +304,25 @@ def chat(dialog, messages, stream=True, **kwargs):
         retrieval_time_cost = (retrieval_ts - generate_keyword_ts) * 1000
         generate_result_time_cost = (finish_chat_ts - retrieval_ts) * 1000
 
+        tk_num = num_tokens_from_string(think+answer)
         prompt += "\n\n### Query:\n%s" % " ".join(questions)
-        prompt = f"{prompt}\n\n - Total: {total_time_cost:.1f}ms\n  - Check LLM: {check_llm_time_cost:.1f}ms\n  - Create retriever: {create_retriever_time_cost:.1f}ms\n  - Bind embedding: {bind_embedding_time_cost:.1f}ms\n  - Bind LLM: {bind_llm_time_cost:.1f}ms\n  - Tune question: {refine_question_time_cost:.1f}ms\n  - Bind reranker: {bind_reranker_time_cost:.1f}ms\n  - Generate keyword: {generate_keyword_time_cost:.1f}ms\n  - Retrieval: {retrieval_time_cost:.1f}ms\n  - Generate answer: {generate_result_time_cost:.1f}ms"
+        prompt = (
+                f"{prompt}\n\n"
+                "## Time elapsed:\n"
+                f"  - Total: {total_time_cost:.1f}ms\n"
+                f"  - Check LLM: {check_llm_time_cost:.1f}ms\n"
+                f"  - Create retriever: {create_retriever_time_cost:.1f}ms\n"
+                f"  - Bind embedding: {bind_embedding_time_cost:.1f}ms\n"
+                f"  - Bind LLM: {bind_llm_time_cost:.1f}ms\n"
+                f"  - Tune question: {refine_question_time_cost:.1f}ms\n"
+                f"  - Bind reranker: {bind_reranker_time_cost:.1f}ms\n"
+                f"  - Generate keyword: {generate_keyword_time_cost:.1f}ms\n"
+                f"  - Retrieval: {retrieval_time_cost:.1f}ms\n"
+                f"  - Generate answer: {generate_result_time_cost:.1f}ms\n\n"
+                "## Token usage:\n"
+                f"  - Generated tokens(approximately): {tk_num}\n"
+                f"  - Token speed: {int(tk_num/(generate_result_time_cost/1000.))}/s"
+        )
         return {"answer": think+answer, "reference": refs, "prompt": re.sub(r"\n", "  \n", prompt), "created_at": time.time()}
 
     if stream: