[ContextAugmentedFunctionAgent] multi tool function call with retrieval #148
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
w5688414
changed the title
w5688414
changed the title
w5688414
changed the title
w5688414
changed the title
sijunhe
reviewed
Dec 18, 2023
erniebot-agent/erniebot_agent/agents/functional_agent_with_retrieval.py
Outdated
Show resolved
Hide resolved
erniebot-agent/erniebot_agent/agents/functional_agent_with_retrieval.py
Outdated
Show resolved
Hide resolved
| # return response | ||
| tool_ret_json = json.dumps({"documents": outputs}, ensure_ascii=False) | ||
| # Direct Prompt | ||
| next_step_input = HumanMessage(content=f"问题：{prompt}，要求：请在第一步执行检索的操作,并且检索只允许调用一次") |
There was a problem hiding this comment.
FunctionalAgentWithRetrievalScoreTool和FunctionalAgentWithRetrievalTool 完全分不出来了
There was a problem hiding this comment.
FunctionAgentWithRetrievalTool是模拟一次function call的调用
FunctionAgentWithRetrievalScoreTool是通过prompt的方式来引导function call调用检索
| @@ -298,3 +385,36 @@ async def _maybe_retrieval( | |||
| results = {} | |||
| results["documents"] = documents | |||
| return results | |||
|
|
|||
|
|
|||
| class FunctionalAgentWithQueryPlanning(FunctionalAgent): | |||
There was a problem hiding this comment.
这个是把retrieval 当成tool的类，planning部分用的是functional agent默认的，可能后面会加入一些后处理
| documents: List[SearchResponseDocument] = Field(description="检索结果，内容和用户输入query相关的段落") | ||
|
|
||
|
|
||
| class OpenAISearchTool(Tool): |
There was a problem hiding this comment.
这里面的db用的是langchain 的faiss，faiss的search接口和返回的参数跟欧若拉不一样，所以重新写了一个tool
| llm=llm, | ||
| knowledge_base=baizhong_db, | ||
| top_k=3, | ||
| tools=toolkit.get_tools() + [retrieval_tool], | ||
| tools=toolkit.get_tools() + [NotesTool(), retrieval_tool], |
There was a problem hiding this comment.
为啥这里还需要传入retrieval_tool这个工具呢？
Comment on lines
158
to
167
| tools=[NotesTool(), retrieval_tool], | ||
| memory=memory, | ||
| ) | ||
| elif args.retrieval_type == "context_aug": | ||
| agent = ContextAugmentedFunctionalAgent( # type: ignore | ||
| llm=llm, | ||
| knowledge_base=baizhong_db, | ||
| top_k=3, | ||
| threshold=0.1, | ||
| tools=[NotesTool(), retrieval_tool], |
There was a problem hiding this comment.
这些agent的tools哪些应该传入retrieval_tool, 哪些不应该传入，需要想清楚
There was a problem hiding this comment.
已删除functional_agent_with_retrieval_example.py
…rieval.py Co-authored-by: Sijun He <sijun.he@hotmail.com>
w5688414
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
TODO:
PR会进行拆分：