Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-06 03:20:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix Baby AGI notebooks (#2882)

Browse Source 
- fix broken notebook cell in
ae485b623d
- Python Black formatting
This commit is contained in:
ecneladis 2023-04-14 16:40:04 +02:00 committed by GitHub
parent 3c7204d604
commit 1a44b71ddf
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 140 additions and 79 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

95
docs/use_cases/agents/baby_agi.ipynb
View File

@ -38,7 +38,7 @@
"from langchain.llms import BaseLLM\n", "from langchain.llms import BaseLLM\n",
"from langchain.vectorstores.base import VectorStore\n", "from langchain.vectorstores.base import VectorStore\n",
"from pydantic import BaseModel, Field\n", "from pydantic import BaseModel, Field\n",
"from langchain.chains.base import Chain\n" "from langchain.chains.base import Chain"
] ]
}, },
{ {
@ -73,6 +73,7 @@
"embeddings_model = OpenAIEmbeddings()\n", "embeddings_model = OpenAIEmbeddings()\n",
"# Initialize the vectorstore as empty\n", "# Initialize the vectorstore as empty\n",
"import faiss\n", "import faiss\n",
"\n",
"embedding_size = 1536\n", "embedding_size = 1536\n",
"index = faiss.IndexFlatL2(embedding_size)\n", "index = faiss.IndexFlatL2(embedding_size)\n",
"vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})" "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
@ -116,7 +117,12 @@
" )\n", " )\n",
" prompt = PromptTemplate(\n", " prompt = PromptTemplate(\n",
" template=task_creation_template,\n", " template=task_creation_template,\n",
" input_variables=[\"result\", \"task_description\", \"incomplete_tasks\", \"objective\"],\n", " input_variables=[\n",
" \"result\",\n",
" \"task_description\",\n",
" \"incomplete_tasks\",\n",
" \"objective\",\n",
" ],\n",
" )\n", " )\n",
" return cls(prompt=prompt, llm=llm, verbose=verbose)" " return cls(prompt=prompt, llm=llm, verbose=verbose)"
] ]
@ -147,7 +153,7 @@
" template=task_prioritization_template,\n", " template=task_prioritization_template,\n",
" input_variables=[\"task_names\", \"next_task_id\", \"objective\"],\n", " input_variables=[\"task_names\", \"next_task_id\", \"objective\"],\n",
" )\n", " )\n",
" return cls(prompt=prompt, llm=llm, verbose=verbose)\n" " return cls(prompt=prompt, llm=llm, verbose=verbose)"
] ]
}, },
{ {
@ -173,7 +179,7 @@
" template=execution_template,\n", " template=execution_template,\n",
" input_variables=[\"objective\", \"context\", \"task\"],\n", " input_variables=[\"objective\", \"context\", \"task\"],\n",
" )\n", " )\n",
" return cls(prompt=prompt, llm=llm, verbose=verbose)\n" " return cls(prompt=prompt, llm=llm, verbose=verbose)"
] ]
}, },
{ {
@ -193,11 +199,22 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def get_next_task(task_creation_chain: LLMChain, result: Dict, task_description: str, task_list: List[str], objective: str) -> List[Dict]:\n", "def get_next_task(\n",
" task_creation_chain: LLMChain,\n",
" result: Dict,\n",
" task_description: str,\n",
" task_list: List[str],\n",
" objective: str,\n",
") -> List[Dict]:\n",
" \"\"\"Get the next task.\"\"\"\n", " \"\"\"Get the next task.\"\"\"\n",
" incomplete_tasks = \", \".join(task_list)\n", " incomplete_tasks = \", \".join(task_list)\n",
" response = task_creation_chain.run(result=result, task_description=task_description, incomplete_tasks=incomplete_tasks, objective=objective)\n", " response = task_creation_chain.run(\n",
" new_tasks = response.split('\\n')\n", " result=result,\n",
" task_description=task_description,\n",
" incomplete_tasks=incomplete_tasks,\n",
" objective=objective,\n",
" )\n",
" new_tasks = response.split(\"\\n\")\n",
" return [{\"task_name\": task_name} for task_name in new_tasks if task_name.strip()]" " return [{\"task_name\": task_name} for task_name in new_tasks if task_name.strip()]"
] ]
}, },
@ -208,12 +225,19 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def prioritize_tasks(task_prioritization_chain: LLMChain, this_task_id: int, task_list: List[Dict], objective: str) -> List[Dict]:\n", "def prioritize_tasks(\n",
" task_prioritization_chain: LLMChain,\n",
" this_task_id: int,\n",
" task_list: List[Dict],\n",
" objective: str,\n",
") -> List[Dict]:\n",
" \"\"\"Prioritize tasks.\"\"\"\n", " \"\"\"Prioritize tasks.\"\"\"\n",
" task_names = [t[\"task_name\"] for t in task_list]\n", " task_names = [t[\"task_name\"] for t in task_list]\n",
" next_task_id = int(this_task_id) + 1\n", " next_task_id = int(this_task_id) + 1\n",
" response = task_prioritization_chain.run(task_names=task_names, next_task_id=next_task_id, objective=objective)\n", " response = task_prioritization_chain.run(\n",
" new_tasks = response.split('\\n')\n", " task_names=task_names, next_task_id=next_task_id, objective=objective\n",
" )\n",
" new_tasks = response.split(\"\\n\")\n",
" prioritized_task_list = []\n", " prioritized_task_list = []\n",
" for task_string in new_tasks:\n", " for task_string in new_tasks:\n",
" if not task_string.strip():\n", " if not task_string.strip():\n",
@ -239,9 +263,12 @@
" if not results:\n", " if not results:\n",
" return []\n", " return []\n",
" sorted_results, _ = zip(*sorted(results, key=lambda x: x[1], reverse=True))\n", " sorted_results, _ = zip(*sorted(results, key=lambda x: x[1], reverse=True))\n",
" return [str(item.metadata['task']) for item in sorted_results]\n", " return [str(item.metadata[\"task\"]) for item in sorted_results]\n",
"\n", "\n",
"def execute_task(vectorstore, execution_chain: LLMChain, objective: str, task: str, k: int = 5) -> str:\n", "\n",
"def execute_task(\n",
" vectorstore, execution_chain: LLMChain, objective: str, task: str, k: int = 5\n",
") -> str:\n",
" \"\"\"Execute a task.\"\"\"\n", " \"\"\"Execute a task.\"\"\"\n",
" context = _get_top_tasks(vectorstore, query=objective, k=k)\n", " context = _get_top_tasks(vectorstore, query=objective, k=k)\n",
" return execution_chain.run(objective=objective, context=context, task=task)" " return execution_chain.run(objective=objective, context=context, task=task)"
@ -254,7 +281,6 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"\n",
"class BabyAGI(Chain, BaseModel):\n", "class BabyAGI(Chain, BaseModel):\n",
" \"\"\"Controller model for the BabyAGI agent.\"\"\"\n", " \"\"\"Controller model for the BabyAGI agent.\"\"\"\n",
"\n", "\n",
@ -265,9 +291,10 @@
" task_id_counter: int = Field(1)\n", " task_id_counter: int = Field(1)\n",
" vectorstore: VectorStore = Field(init=False)\n", " vectorstore: VectorStore = Field(init=False)\n",
" max_iterations: Optional[int] = None\n", " max_iterations: Optional[int] = None\n",
" \n", "\n",
" class Config:\n", " class Config:\n",
" \"\"\"Configuration for this pydantic object.\"\"\"\n", " \"\"\"Configuration for this pydantic object.\"\"\"\n",
"\n",
" arbitrary_types_allowed = True\n", " arbitrary_types_allowed = True\n",
"\n", "\n",
" def add_task(self, task: Dict):\n", " def add_task(self, task: Dict):\n",
@ -285,18 +312,18 @@
" def print_task_result(self, result: str):\n", " def print_task_result(self, result: str):\n",
" print(\"\\033[93m\\033[1m\" + \"\\n*****TASK RESULT*****\\n\" + \"\\033[0m\\033[0m\")\n", " print(\"\\033[93m\\033[1m\" + \"\\n*****TASK RESULT*****\\n\" + \"\\033[0m\\033[0m\")\n",
" print(result)\n", " print(result)\n",
" \n", "\n",
" @property\n", " @property\n",
" def input_keys(self) -> List[str]:\n", " def input_keys(self) -> List[str]:\n",
" return [\"objective\"]\n", " return [\"objective\"]\n",
" \n", "\n",
" @property\n", " @property\n",
" def output_keys(self) -> List[str]:\n", " def output_keys(self) -> List[str]:\n",
" return []\n", " return []\n",
"\n", "\n",
" def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:\n", " def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:\n",
" \"\"\"Run the agent.\"\"\"\n", " \"\"\"Run the agent.\"\"\"\n",
" objective = inputs['objective']\n", " objective = inputs[\"objective\"]\n",
" first_task = inputs.get(\"first_task\", \"Make a todo list\")\n", " first_task = inputs.get(\"first_task\", \"Make a todo list\")\n",
" self.add_task({\"task_id\": 1, \"task_name\": first_task})\n", " self.add_task({\"task_id\": 1, \"task_name\": first_task})\n",
" num_iters = 0\n", " num_iters = 0\n",
@ -325,7 +352,11 @@
"\n", "\n",
" # Step 4: Create new tasks and reprioritize task list\n", " # Step 4: Create new tasks and reprioritize task list\n",
" new_tasks = get_next_task(\n", " new_tasks = get_next_task(\n",
" self.task_creation_chain, result, task[\"task_name\"], [t[\"task_name\"] for t in self.task_list], objective\n", " self.task_creation_chain,\n",
" result,\n",
" task[\"task_name\"],\n",
" [t[\"task_name\"] for t in self.task_list],\n",
" objective,\n",
" )\n", " )\n",
" for new_task in new_tasks:\n", " for new_task in new_tasks:\n",
" self.task_id_counter += 1\n", " self.task_id_counter += 1\n",
@ -333,27 +364,26 @@
" self.add_task(new_task)\n", " self.add_task(new_task)\n",
" self.task_list = deque(\n", " self.task_list = deque(\n",
" prioritize_tasks(\n", " prioritize_tasks(\n",
" self.task_prioritization_chain, this_task_id, list(self.task_list), objective\n", " self.task_prioritization_chain,\n",
" this_task_id,\n",
" list(self.task_list),\n",
" objective,\n",
" )\n", " )\n",
" )\n", " )\n",
" num_iters += 1\n", " num_iters += 1\n",
" if self.max_iterations is not None and num_iters == self.max_iterations:\n", " if self.max_iterations is not None and num_iters == self.max_iterations:\n",
" print(\"\\033[91m\\033[1m\" + \"\\n*****TASK ENDING*****\\n\" + \"\\033[0m\\033[0m\")\n", " print(\n",
" \"\\033[91m\\033[1m\" + \"\\n*****TASK ENDING*****\\n\" + \"\\033[0m\\033[0m\"\n",
" )\n",
" break\n", " break\n",
" return {}\n", " return {}\n",
"\n", "\n",
" @classmethod\n", " @classmethod\n",
" def from_llm(\n", " def from_llm(\n",
" cls,\n", " cls, llm: BaseLLM, vectorstore: VectorStore, verbose: bool = False, **kwargs\n",
" llm: BaseLLM,\n",
" vectorstore: VectorStore,\n",
" verbose: bool = False,\n",
" **kwargs\n",
" ) -> \"BabyAGI\":\n", " ) -> \"BabyAGI\":\n",
" \"\"\"Initialize the BabyAGI Controller.\"\"\"\n", " \"\"\"Initialize the BabyAGI Controller.\"\"\"\n",
" task_creation_chain = TaskCreationChain.from_llm(\n", " task_creation_chain = TaskCreationChain.from_llm(llm, verbose=verbose)\n",
" llm, verbose=verbose\n",
" )\n",
" task_prioritization_chain = TaskPrioritizationChain.from_llm(\n", " task_prioritization_chain = TaskPrioritizationChain.from_llm(\n",
" llm, verbose=verbose\n", " llm, verbose=verbose\n",
" )\n", " )\n",
@ -363,7 +393,7 @@
" task_prioritization_chain=task_prioritization_chain,\n", " task_prioritization_chain=task_prioritization_chain,\n",
" execution_chain=execution_chain,\n", " execution_chain=execution_chain,\n",
" vectorstore=vectorstore,\n", " vectorstore=vectorstore,\n",
" **kwargs\n", " **kwargs,\n",
" )" " )"
] ]
}, },
@ -405,14 +435,11 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# Logging of LLMChains\n", "# Logging of LLMChains\n",
"verbose=False\n", "verbose = False\n",
"# If None, will keep on going forever\n", "# If None, will keep on going forever\n",
"max_iterations: Optional[int] = 3\n", "max_iterations: Optional[int] = 3\n",
"baby_agi = BabyAGI.from_llm(\n", "baby_agi = BabyAGI.from_llm(\n",
" llm=llm,\n", " llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
" vectorstore=vectorstore,\n",
" verbose=verbose,\n",
" max_iterations=max_iterations\n",
")" ")"
] ]
}, },

124
docs/use_cases/agents/baby_agi_with_agent.ipynb
View File

@ -34,7 +34,7 @@
"from langchain.llms import BaseLLM\n", "from langchain.llms import BaseLLM\n",
"from langchain.vectorstores.base import VectorStore\n", "from langchain.vectorstores.base import VectorStore\n",
"from pydantic import BaseModel, Field\n", "from pydantic import BaseModel, Field\n",
"from langchain.chains.base import Chain\n" "from langchain.chains.base import Chain"
] ]
}, },
{ {
@ -54,7 +54,9 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"%pip install faiss-cpu > /dev/null%pip install google-search-results > /dev/nullfrom langchain.vectorstores import FAISS\n", "%pip install faiss-cpu > /dev/null\n",
"%pip install google-search-results > /dev/null\n",
"from langchain.vectorstores import FAISS\n",
"from langchain.docstore import InMemoryDocstore" "from langchain.docstore import InMemoryDocstore"
] ]
}, },
@ -69,6 +71,7 @@
"embeddings_model = OpenAIEmbeddings()\n", "embeddings_model = OpenAIEmbeddings()\n",
"# Initialize the vectorstore as empty\n", "# Initialize the vectorstore as empty\n",
"import faiss\n", "import faiss\n",
"\n",
"embedding_size = 1536\n", "embedding_size = 1536\n",
"index = faiss.IndexFlatL2(embedding_size)\n", "index = faiss.IndexFlatL2(embedding_size)\n",
"vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})" "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
@ -115,7 +118,12 @@
" )\n", " )\n",
" prompt = PromptTemplate(\n", " prompt = PromptTemplate(\n",
" template=task_creation_template,\n", " template=task_creation_template,\n",
" input_variables=[\"result\", \"task_description\", \"incomplete_tasks\", \"objective\"],\n", " input_variables=[\n",
" \"result\",\n",
" \"task_description\",\n",
" \"incomplete_tasks\",\n",
" \"objective\",\n",
" ],\n",
" )\n", " )\n",
" return cls(prompt=prompt, llm=llm, verbose=verbose)" " return cls(prompt=prompt, llm=llm, verbose=verbose)"
] ]
@ -146,7 +154,7 @@
" template=task_prioritization_template,\n", " template=task_prioritization_template,\n",
" input_variables=[\"task_names\", \"next_task_id\", \"objective\"],\n", " input_variables=[\"task_names\", \"next_task_id\", \"objective\"],\n",
" )\n", " )\n",
" return cls(prompt=prompt, llm=llm, verbose=verbose)\n" " return cls(prompt=prompt, llm=llm, verbose=verbose)"
] ]
}, },
{ {
@ -158,20 +166,23 @@
"source": [ "source": [
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n", "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
"from langchain import OpenAI, SerpAPIWrapper, LLMChain\n", "from langchain import OpenAI, SerpAPIWrapper, LLMChain\n",
"todo_prompt = PromptTemplate.from_template(\"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}\")\n", "\n",
"todo_prompt = PromptTemplate.from_template(\n",
" \"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}\"\n",
")\n",
"todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)\n", "todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)\n",
"search = SerpAPIWrapper()\n", "search = SerpAPIWrapper()\n",
"tools = [\n", "tools = [\n",
" Tool(\n", " Tool(\n",
" name = \"Search\",\n", " name=\"Search\",\n",
" func=search.run,\n", " func=search.run,\n",
" description=\"useful for when you need to answer questions about current events\"\n", " description=\"useful for when you need to answer questions about current events\",\n",
" ),\n", " ),\n",
" Tool(\n", " Tool(\n",
" name = \"TODO\",\n", " name=\"TODO\",\n",
" func=todo_chain.run,\n", " func=todo_chain.run,\n",
" description=\"useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!\"\n", " description=\"useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!\",\n",
" )\n", " ),\n",
"]\n", "]\n",
"\n", "\n",
"\n", "\n",
@ -179,10 +190,10 @@
"suffix = \"\"\"Question: {task}\n", "suffix = \"\"\"Question: {task}\n",
"{agent_scratchpad}\"\"\"\n", "{agent_scratchpad}\"\"\"\n",
"prompt = ZeroShotAgent.create_prompt(\n", "prompt = ZeroShotAgent.create_prompt(\n",
" tools, \n", " tools,\n",
" prefix=prefix, \n", " prefix=prefix,\n",
" suffix=suffix, \n", " suffix=suffix,\n",
" input_variables=[\"objective\", \"task\", \"context\",\"agent_scratchpad\"]\n", " input_variables=[\"objective\", \"task\", \"context\", \"agent_scratchpad\"],\n",
")" ")"
] ]
}, },
@ -203,11 +214,22 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def get_next_task(task_creation_chain: LLMChain, result: Dict, task_description: str, task_list: List[str], objective: str) -> List[Dict]:\n", "def get_next_task(\n",
" task_creation_chain: LLMChain,\n",
" result: Dict,\n",
" task_description: str,\n",
" task_list: List[str],\n",
" objective: str,\n",
") -> List[Dict]:\n",
" \"\"\"Get the next task.\"\"\"\n", " \"\"\"Get the next task.\"\"\"\n",
" incomplete_tasks = \", \".join(task_list)\n", " incomplete_tasks = \", \".join(task_list)\n",
" response = task_creation_chain.run(result=result, task_description=task_description, incomplete_tasks=incomplete_tasks, objective=objective)\n", " response = task_creation_chain.run(\n",
" new_tasks = response.split('\\n')\n", " result=result,\n",
" task_description=task_description,\n",
" incomplete_tasks=incomplete_tasks,\n",
" objective=objective,\n",
" )\n",
" new_tasks = response.split(\"\\n\")\n",
" return [{\"task_name\": task_name} for task_name in new_tasks if task_name.strip()]" " return [{\"task_name\": task_name} for task_name in new_tasks if task_name.strip()]"
] ]
}, },
@ -218,12 +240,19 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def prioritize_tasks(task_prioritization_chain: LLMChain, this_task_id: int, task_list: List[Dict], objective: str) -> List[Dict]:\n", "def prioritize_tasks(\n",
" task_prioritization_chain: LLMChain,\n",
" this_task_id: int,\n",
" task_list: List[Dict],\n",
" objective: str,\n",
") -> List[Dict]:\n",
" \"\"\"Prioritize tasks.\"\"\"\n", " \"\"\"Prioritize tasks.\"\"\"\n",
" task_names = [t[\"task_name\"] for t in task_list]\n", " task_names = [t[\"task_name\"] for t in task_list]\n",
" next_task_id = int(this_task_id) + 1\n", " next_task_id = int(this_task_id) + 1\n",
" response = task_prioritization_chain.run(task_names=task_names, next_task_id=next_task_id, objective=objective)\n", " response = task_prioritization_chain.run(\n",
" new_tasks = response.split('\\n')\n", " task_names=task_names, next_task_id=next_task_id, objective=objective\n",
" )\n",
" new_tasks = response.split(\"\\n\")\n",
" prioritized_task_list = []\n", " prioritized_task_list = []\n",
" for task_string in new_tasks:\n", " for task_string in new_tasks:\n",
" if not task_string.strip():\n", " if not task_string.strip():\n",
@ -249,9 +278,12 @@
" if not results:\n", " if not results:\n",
" return []\n", " return []\n",
" sorted_results, _ = zip(*sorted(results, key=lambda x: x[1], reverse=True))\n", " sorted_results, _ = zip(*sorted(results, key=lambda x: x[1], reverse=True))\n",
" return [str(item.metadata['task']) for item in sorted_results]\n", " return [str(item.metadata[\"task\"]) for item in sorted_results]\n",
"\n", "\n",
"def execute_task(vectorstore, execution_chain: LLMChain, objective: str, task: str, k: int = 5) -> str:\n", "\n",
"def execute_task(\n",
" vectorstore, execution_chain: LLMChain, objective: str, task: str, k: int = 5\n",
") -> str:\n",
" \"\"\"Execute a task.\"\"\"\n", " \"\"\"Execute a task.\"\"\"\n",
" context = _get_top_tasks(vectorstore, query=objective, k=k)\n", " context = _get_top_tasks(vectorstore, query=objective, k=k)\n",
" return execution_chain.run(objective=objective, context=context, task=task)" " return execution_chain.run(objective=objective, context=context, task=task)"
@ -264,7 +296,6 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"\n",
"class BabyAGI(Chain, BaseModel):\n", "class BabyAGI(Chain, BaseModel):\n",
" \"\"\"Controller model for the BabyAGI agent.\"\"\"\n", " \"\"\"Controller model for the BabyAGI agent.\"\"\"\n",
"\n", "\n",
@ -275,9 +306,10 @@
" task_id_counter: int = Field(1)\n", " task_id_counter: int = Field(1)\n",
" vectorstore: VectorStore = Field(init=False)\n", " vectorstore: VectorStore = Field(init=False)\n",
" max_iterations: Optional[int] = None\n", " max_iterations: Optional[int] = None\n",
" \n", "\n",
" class Config:\n", " class Config:\n",
" \"\"\"Configuration for this pydantic object.\"\"\"\n", " \"\"\"Configuration for this pydantic object.\"\"\"\n",
"\n",
" arbitrary_types_allowed = True\n", " arbitrary_types_allowed = True\n",
"\n", "\n",
" def add_task(self, task: Dict):\n", " def add_task(self, task: Dict):\n",
@ -295,18 +327,18 @@
" def print_task_result(self, result: str):\n", " def print_task_result(self, result: str):\n",
" print(\"\\033[93m\\033[1m\" + \"\\n*****TASK RESULT*****\\n\" + \"\\033[0m\\033[0m\")\n", " print(\"\\033[93m\\033[1m\" + \"\\n*****TASK RESULT*****\\n\" + \"\\033[0m\\033[0m\")\n",
" print(result)\n", " print(result)\n",
" \n", "\n",
" @property\n", " @property\n",
" def input_keys(self) -> List[str]:\n", " def input_keys(self) -> List[str]:\n",
" return [\"objective\"]\n", " return [\"objective\"]\n",
" \n", "\n",
" @property\n", " @property\n",
" def output_keys(self) -> List[str]:\n", " def output_keys(self) -> List[str]:\n",
" return []\n", " return []\n",
"\n", "\n",
" def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:\n", " def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:\n",
" \"\"\"Run the agent.\"\"\"\n", " \"\"\"Run the agent.\"\"\"\n",
" objective = inputs['objective']\n", " objective = inputs[\"objective\"]\n",
" first_task = inputs.get(\"first_task\", \"Make a todo list\")\n", " first_task = inputs.get(\"first_task\", \"Make a todo list\")\n",
" self.add_task({\"task_id\": 1, \"task_name\": first_task})\n", " self.add_task({\"task_id\": 1, \"task_name\": first_task})\n",
" num_iters = 0\n", " num_iters = 0\n",
@ -335,7 +367,11 @@
"\n", "\n",
" # Step 4: Create new tasks and reprioritize task list\n", " # Step 4: Create new tasks and reprioritize task list\n",
" new_tasks = get_next_task(\n", " new_tasks = get_next_task(\n",
" self.task_creation_chain, result, task[\"task_name\"], [t[\"task_name\"] for t in self.task_list], objective\n", " self.task_creation_chain,\n",
" result,\n",
" task[\"task_name\"],\n",
" [t[\"task_name\"] for t in self.task_list],\n",
" objective,\n",
" )\n", " )\n",
" for new_task in new_tasks:\n", " for new_task in new_tasks:\n",
" self.task_id_counter += 1\n", " self.task_id_counter += 1\n",
@ -343,40 +379,41 @@
" self.add_task(new_task)\n", " self.add_task(new_task)\n",
" self.task_list = deque(\n", " self.task_list = deque(\n",
" prioritize_tasks(\n", " prioritize_tasks(\n",
" self.task_prioritization_chain, this_task_id, list(self.task_list), objective\n", " self.task_prioritization_chain,\n",
" this_task_id,\n",
" list(self.task_list),\n",
" objective,\n",
" )\n", " )\n",
" )\n", " )\n",
" num_iters += 1\n", " num_iters += 1\n",
" if self.max_iterations is not None and num_iters == self.max_iterations:\n", " if self.max_iterations is not None and num_iters == self.max_iterations:\n",
" print(\"\\033[91m\\033[1m\" + \"\\n*****TASK ENDING*****\\n\" + \"\\033[0m\\033[0m\")\n", " print(\n",
" \"\\033[91m\\033[1m\" + \"\\n*****TASK ENDING*****\\n\" + \"\\033[0m\\033[0m\"\n",
" )\n",
" break\n", " break\n",
" return {}\n", " return {}\n",
"\n", "\n",
" @classmethod\n", " @classmethod\n",
" def from_llm(\n", " def from_llm(\n",
" cls,\n", " cls, llm: BaseLLM, vectorstore: VectorStore, verbose: bool = False, **kwargs\n",
" llm: BaseLLM,\n",
" vectorstore: VectorStore,\n",
" verbose: bool = False,\n",
" **kwargs\n",
" ) -> \"BabyAGI\":\n", " ) -> \"BabyAGI\":\n",
" \"\"\"Initialize the BabyAGI Controller.\"\"\"\n", " \"\"\"Initialize the BabyAGI Controller.\"\"\"\n",
" task_creation_chain = TaskCreationChain.from_llm(\n", " task_creation_chain = TaskCreationChain.from_llm(llm, verbose=verbose)\n",
" llm, verbose=verbose\n",
" )\n",
" task_prioritization_chain = TaskPrioritizationChain.from_llm(\n", " task_prioritization_chain = TaskPrioritizationChain.from_llm(\n",
" llm, verbose=verbose\n", " llm, verbose=verbose\n",
" )\n", " )\n",
" llm_chain = LLMChain(llm=llm, prompt=prompt)\n", " llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
" tool_names = [tool.name for tool in tools]\n", " tool_names = [tool.name for tool in tools]\n",
" agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)\n", " agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)\n",
" agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)\n", " agent_executor = AgentExecutor.from_agent_and_tools(\n",
" agent=agent, tools=tools, verbose=True\n",
" )\n",
" return cls(\n", " return cls(\n",
" task_creation_chain=task_creation_chain,\n", " task_creation_chain=task_creation_chain,\n",
" task_prioritization_chain=task_prioritization_chain,\n", " task_prioritization_chain=task_prioritization_chain,\n",
" execution_chain=agent_executor,\n", " execution_chain=agent_executor,\n",
" vectorstore=vectorstore,\n", " vectorstore=vectorstore,\n",
" **kwargs\n", " **kwargs,\n",
" )" " )"
] ]
}, },
@ -418,14 +455,11 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# Logging of LLMChains\n", "# Logging of LLMChains\n",
"verbose=False\n", "verbose = False\n",
"# If None, will keep on going forever\n", "# If None, will keep on going forever\n",
"max_iterations: Optional[int] = 3\n", "max_iterations: Optional[int] = 3\n",
"baby_agi = BabyAGI.from_llm(\n", "baby_agi = BabyAGI.from_llm(\n",
" llm=llm,\n", " llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
" vectorstore=vectorstore,\n",
" verbose=verbose,\n",
" max_iterations=max_iterations\n",
")" ")"
] ]
}, },