Add high-quality settings

README.md

@@ -139,6 +139,21 @@ or I can use the normal ask
 pqa -i nanomaterials ask 'Are there nm scale features in thermoelectric materials?'
 ```
 
+Both the CLI and module have pre-configured settings based on prior performance and our publications, they can be invoked as follows:
+
+```
+pqa --settings <setting name> ask 'Are there nm scale features in thermoelectric materials?'
+```
+
+Here is a table of some useful settings:
+
+| Setting Name | Description                                                                                                                  |
+| ------------ | ---------------------------------------------------------------------------------------------------------------------------- |
+| high_quality | Highly performant, relatively expensive (due to having `evidence_k` = 15) query using a `ToolSelector` agent.                |
+| fast         | Setting to get answers cheaply and quickly.                                                                                  |
+| wikicrow     | Setting to emulate the Wikipedia article writing used in our WikiCrow publication.                                           |
+| contracrow   | Setting to find contradictions in papers, your query should be a claim that needs to be flagged as a contradiction (or not). |
+
 ### Module Usage
 
 PaperQA's full workflow can be accessed via Python directly:

paperqa/agents/tools.py

@@ -70,7 +70,7 @@ async def paper_search(
         """
         Search for papers to increase the paper count.
 
-        Repeat previous calls with the same query and years to continue a search.
+        Repeat previous calls with the same query and years to continue a search. Only repeat a maximum of twice.
         This tool can be called concurrently.
         This tool introduces novel papers, so invoke this tool when just beginning or when unsatisfied with the current evidence.
 
@@ -210,9 +210,7 @@ class GenerateAnswer(NamedTool):
     def did_not_fail_to_answer(cls, message: str) -> bool:
         return not message.startswith(cls.FAILED_TO_ANSWER)
 
-    async def gen_answer(
-        self, question: str, state: EnvironmentState  # noqa: ARG002
-    ) -> str:
+    async def gen_answer(self, question: str, state: EnvironmentState) -> str:
         """
         Ask a model to propose an answer using current evidence.
 
@@ -224,6 +222,7 @@ async def gen_answer(
             question: Question to be answered.
             state: Current state.
         """
+        logger.info(f"Generating answer for '{question}'.")
         # TODO: Should we allow the agent to change the question?
         # self.answer.question = query
         state.answer = await state.docs.aquery(

paperqa/configs/high_quality.json

@@ -0,0 +1,18 @@
+{
+  "answer": {
+    "evidence_k": 20,
+    "answer_max_sources": 5,
+    "max_concurrent_requests": 10
+  },
+  "parsing": {
+    "use_doc_details": true,
+    "chunk_size": 7000,
+    "overlap": 250
+  },
+  "prompts": {
+    "use_json": true
+  },
+  "agent": {
+    "agent_type": "ToolSelector"
+  }
+}