add agent components

libs/langchain/langchain/agents/format_intermediate_steps/react_single_input.py

@@ -0,0 +1,6 @@
+def format_react_single_input(intermediate_steps, observation_prefix:str = "Observation", llm_prefix: str = "Thought"):
+    thoughts = ""
+    for action, observation in intermediate_steps:
+        thoughts += action.log
+        thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
+    return thoughts

libs/langchain/langchain/agents/format_tools.py

@@ -0,0 +1,2 @@
+def format_tools_with_description(tools):
+    return "\n".join([f"{tool.name}: {tool.description}" for tool in tools])

libs/langchain/langchain/agents/mrkl/output_parser.py

@@ -1,72 +1,13 @@
-import re
-from typing import Union
-
-from langchain.agents.agent import AgentOutputParser
+from langchain.agents.output_parsers.react_single_input import ReActSingleInputOutputParser
 from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
-from langchain.schema import AgentAction, AgentFinish, OutputParserException
-
-FINAL_ANSWER_ACTION = "Final Answer:"
-MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE = (
-    "Invalid Format: Missing 'Action:' after 'Thought:"
-)
-MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE = (
-    "Invalid Format: Missing 'Action Input:' after 'Action:'"
-)
-FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = (
-    "Parsing LLM output produced both a final answer and a parse-able action:"
-)
 
 
-class MRKLOutputParser(AgentOutputParser):
+class MRKLOutputParser(ReActSingleInputOutputParser):
     """MRKL Output parser for the chat agent."""
 
     def get_format_instructions(self) -> str:
         return FORMAT_INSTRUCTIONS
 
-    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
-        includes_answer = FINAL_ANSWER_ACTION in text
-        regex = (
-            r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"
-        )
-        action_match = re.search(regex, text, re.DOTALL)
-        if action_match:
-            if includes_answer:
-                raise OutputParserException(
-                    f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
-                )
-            action = action_match.group(1).strip()
-            action_input = action_match.group(2)
-            tool_input = action_input.strip(" ")
-            # ensure if its a well formed SQL query we don't remove any trailing " chars
-            if tool_input.startswith("SELECT ") is False:
-                tool_input = tool_input.strip('"')
-
-            return AgentAction(action, tool_input, text)
-
-        elif includes_answer:
-            return AgentFinish(
-                {"output": text.split(FINAL_ANSWER_ACTION)[-1].strip()}, text
-            )
-
-        if not re.search(r"Action\s*\d*\s*:[\s]*(.*?)", text, re.DOTALL):
-            raise OutputParserException(
-                f"Could not parse LLM output: `{text}`",
-                observation=MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE,
-                llm_output=text,
-                send_to_llm=True,
-            )
-        elif not re.search(
-            r"[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)", text, re.DOTALL
-        ):
-            raise OutputParserException(
-                f"Could not parse LLM output: `{text}`",
-                observation=MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE,
-                llm_output=text,
-                send_to_llm=True,
-            )
-        else:
-            raise OutputParserException(f"Could not parse LLM output: `{text}`")
-
     @property
     def _type(self) -> str:
         return "mrkl"

libs/langchain/langchain/agents/output_parsers/react_single_input.py

@@ -0,0 +1,72 @@
+import re
+from typing import Union
+
+from langchain.agents.agent import AgentOutputParser
+from langchain.schema import AgentAction, AgentFinish, OutputParserException
+
+FINAL_ANSWER_ACTION = "Final Answer:"
+MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE = (
+    "Invalid Format: Missing 'Action:' after 'Thought:"
+)
+MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE = (
+    "Invalid Format: Missing 'Action Input:' after 'Action:'"
+)
+FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = (
+    "Parsing LLM output produced both a final answer and a parse-able action:"
+)
+
+
+class ReActSingleInputOutputParser(AgentOutputParser):
+    """Parser for ReAct format ."""
+
+    def get_format_instructions(self) -> str:
+        pass
+
+    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
+        includes_answer = FINAL_ANSWER_ACTION in text
+        regex = (
+            r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"
+        )
+        action_match = re.search(regex, text, re.DOTALL)
+        if action_match:
+            if includes_answer:
+                raise OutputParserException(
+                    f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
+                )
+            action = action_match.group(1).strip()
+            action_input = action_match.group(2)
+            tool_input = action_input.strip(" ")
+            # ensure if it's a well-formed SQL query we don't remove any trailing " chars
+            if tool_input.startswith("SELECT ") is False:
+                tool_input = tool_input.strip('"')
+
+            return AgentAction(action, tool_input, text)
+
+        elif includes_answer:
+            return AgentFinish(
+                {"output": text.split(FINAL_ANSWER_ACTION)[-1].strip()}, text
+            )
+
+        if not re.search(r"Action\s*\d*\s*:[\s]*(.*?)", text, re.DOTALL):
+            raise OutputParserException(
+                f"Could not parse LLM output: `{text}`",
+                observation=MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE,
+                llm_output=text,
+                send_to_llm=True,
+            )
+        elif not re.search(
+            r"[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)", text, re.DOTALL
+        ):
+            raise OutputParserException(
+                f"Could not parse LLM output: `{text}`",
+                observation=MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE,
+                llm_output=text,
+                send_to_llm=True,
+            )
+        else:
+            raise OutputParserException(f"Could not parse LLM output: `{text}`")
+
+    @property
+    def _type(self) -> str:
+        return "react-single-input"
+