Don't try to store an empty result

[eraviart]

When an agent fails (for example: llama_generate: error: prompt is too long (2215 tokens, max 1996)), it returns no result. This PR ensures that a call to store_result doesn't raise an exception when result is empty.

So, it fixes the exception below (but doesn't fix the "prompt too long" error that occurs before):

llama_generate: error: prompt is too long (2215 tokens, max 1996)
Exception in thread Thread-2:
Traceback (most recent call last):
  File "/usr/lib/python3.9/threading.py", line 954, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.9/threading.py", line 892, in run
    self._target(*self._args, **self._kwargs)
  File "~/agent-llm/AgentLLM.py", line 282, in run_task
    task = self.execute_next_task()
  File "~/agent-llm/AgentLLM.py", line 254, in execute_next_task
    self.response = self.execution_agent(self.primary_objective, this_task_name, this_task_id)
  File "~/agent-llm/AgentLLM.py", line 221, in execution_agent
    self.response = self.run(prompt)
  File "~/agent-llm/AgentLLM.py", line 73, in run
    self.store_result(task, self.response)
  File "~/agent-llm/AgentLLM.py", line 110, in store_result
    self.collection.add(ids=result_id, documents=result, metadatas={"task": task_name, "result": result})
  File "~/agent-llm/.venv/lib/python3.9/site-packages/chromadb/api/models/Collection.py", line 89, in add
    raise ValueError("You must provide either embeddings or documents, or both")
ValueError: You must provide either embeddings or documents, or both

[Josh-XT]

Thanks again for the contributions!