fix basic search

Author: jgbradley1

graphrag/api/query.py

@@ -1108,8 +1108,6 @@ async def basic_search_streaming(
     vector_store_args = {}
     for index, store in config.vector_store.items():
         vector_store_args[index] = store.model_dump()
-    else:
-        vector_store_args = None
     logger.info(f"Vector Store Args: {redact(vector_store_args)}")  # type: ignore # noqa
 
     description_embedding_store = get_embedding_store(

graphrag/query/structured_search/basic_search/search.py

@@ -121,72 +121,6 @@ async def asearch(
                 output_tokens=0,
             )
 
-    def search(
-        self,
-        query: str,
-        conversation_history: ConversationHistory | None = None,
-        **kwargs,
-    ) -> SearchResult:
-        """Build basic search context that fits a single context window and generate answer for the user question."""
-        start_time = time.time()
-        search_prompt = ""
-        llm_calls, prompt_tokens, output_tokens = {}, {}, {}
-        context_result = self.context_builder.build_context(
-            query=query,
-            conversation_history=conversation_history,
-            **kwargs,
-            **self.context_builder_params,
-        )
-        llm_calls["build_context"] = context_result.llm_calls
-        prompt_tokens["build_context"] = context_result.prompt_tokens
-        output_tokens["build_context"] = context_result.output_tokens
-
-        log.info("GENERATE ANSWER: %d. QUERY: %s", start_time, query)
-        try:
-            search_prompt = self.system_prompt.format(
-                context_data=context_result.context_chunks,
-                response_type=self.response_type,
-            )
-            search_messages = [
-                {"role": "system", "content": search_prompt},
-                {"role": "user", "content": query},
-            ]
-
-            response = self.llm.generate(
-                messages=search_messages,
-                streaming=True,
-                callbacks=self.callbacks,
-                **self.llm_params,
-            )
-            llm_calls["response"] = 1
-            prompt_tokens["response"] = num_tokens(search_prompt, self.token_encoder)
-            output_tokens["response"] = num_tokens(response, self.token_encoder)
-
-            return SearchResult(
-                response=response,
-                context_data=context_result.context_records,
-                context_text=context_result.context_chunks,
-                completion_time=time.time() - start_time,
-                llm_calls=sum(llm_calls.values()),
-                prompt_tokens=sum(prompt_tokens.values()),
-                output_tokens=sum(output_tokens.values()),
-                llm_calls_categories=llm_calls,
-                prompt_tokens_categories=prompt_tokens,
-                output_tokens_categories=output_tokens,
-            )
-
-        except Exception:
-            log.exception("Exception in _map_response_single_batch")
-            return SearchResult(
-                response="",
-                context_data=context_result.context_records,
-                context_text=context_result.context_chunks,
-                completion_time=time.time() - start_time,
-                llm_calls=1,
-                prompt_tokens=num_tokens(search_prompt, self.token_encoder),
-                output_tokens=0,
-            )
-
     async def astream_search(
         self,
         query: str,