Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423)

### What problem does this PR solve?

#9869

### Type of change

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

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>

agent/canvas.py

@@ -153,6 +153,16 @@ class Graph:
     def get_tenant_id(self):
         return self._tenant_id
 
+    def get_variable_value(self, exp: str) -> Any:
+        exp = exp.strip("{").strip("}").strip(" ").strip("{").strip("}")
+        if exp.find("@") < 0:
+            return self.globals[exp]
+        cpn_id, var_nm = exp.split("@")
+        cpn = self.get_component(cpn_id)
+        if not cpn:
+            raise Exception(f"Can't find variable: '{cpn_id}@{var_nm}'")
+        return cpn["obj"].output(var_nm)
+
 
 class Canvas(Graph):
 
@@ -406,16 +416,6 @@ class Canvas(Graph):
             return False
         return True
 
-    def get_variable_value(self, exp: str) -> Any:
-        exp = exp.strip("{").strip("}").strip(" ").strip("{").strip("}")
-        if exp.find("@") < 0:
-            return self.globals[exp]
-        cpn_id, var_nm = exp.split("@")
-        cpn = self.get_component(cpn_id)
-        if not cpn:
-            raise Exception(f"Can't find variable: '{cpn_id}@{var_nm}'")
-        return cpn["obj"].output(var_nm)
-
     def get_history(self, window_size):
         convs = []
         if window_size <= 0:

agent/component/llm.py

@@ -101,6 +101,8 @@ class LLM(ComponentBase):
 
     def get_input_elements(self) -> dict[str, Any]:
         res = self.get_input_elements_from_text(self._param.sys_prompt)
+        if isinstance(self._param.prompts, str):
+            self._param.prompts = [{"role": "user", "content": self._param.prompts}]
         for prompt in self._param.prompts:
             d = self.get_input_elements_from_text(prompt["content"])
             res.update(d)
@@ -112,6 +114,17 @@ class LLM(ComponentBase):
     def add2system_prompt(self, txt):
         self._param.sys_prompt += txt
 
+    def _sys_prompt_and_msg(self, msg, args):
+        if isinstance(self._param.prompts, str):
+            self._param.prompts = [{"role": "user", "content": self._param.prompts}]
+        for p in self._param.prompts:
+            if msg and msg[-1]["role"] == p["role"]:
+                continue
+            p = deepcopy(p)
+            p["content"] = self.string_format(p["content"], args)
+            msg.append(p)
+        return msg, self.string_format(self._param.sys_prompt, args)
+
     def _prepare_prompt_variables(self):
         if self._param.visual_files_var:
             self.imgs = self._canvas.get_variable_value(self._param.visual_files_var)
@@ -127,7 +140,6 @@ class LLM(ComponentBase):
 
         args = {}
         vars = self.get_input_elements() if not self._param.debug_inputs else self._param.debug_inputs
-        sys_prompt = self._param.sys_prompt
         for k, o in vars.items():
             args[k] = o["value"]
             if not isinstance(args[k], str):
@@ -137,16 +149,8 @@ class LLM(ComponentBase):
                     args[k] = str(args[k])
             self.set_input_value(k, args[k])
 
-        msg = self._canvas.get_history(self._param.message_history_window_size)[:-1]
-        for p in self._param.prompts:
-            if msg and msg[-1]["role"] == p["role"]:
-                continue
-            msg.append(deepcopy(p))
-
-        sys_prompt = self.string_format(sys_prompt, args)
+        msg, sys_prompt = self._sys_prompt_and_msg(self._canvas.get_history(self._param.message_history_window_size)[:-1], args)
         user_defined_prompt, sys_prompt = self._extract_prompts(sys_prompt)
-        for m in msg:
-            m["content"] = self.string_format(m["content"], args)
         if self._param.cite and self._canvas.get_reference()["chunks"]:
             sys_prompt += citation_prompt(user_defined_prompt)