id
stringlengths
14
15
text
stringlengths
30
2.4k
source
stringlengths
48
124
38e7d85f58e8-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsBabyAGI User GuideBabyAGI with ToolsCAMEL Role-Playing Autonomous Cooperat...
https://python.langchain.com/docs/use_cases/agents/multi_modal_output_agent
38e7d85f58e8-2
a parrot playing soccer. Action: GenerateImage Action Input: A parrot wearing a soccer uniform, kicking a soccer ball. Observation: E28BE7C7-D105-41E0-8A5B-2CE21424DFEC Thought: I now have the UUID of the generated image. Final Answer: The UUID of the generated image is E28BE7C7-D105-41E0-8A5B-2CE21424DF...
https://python.langchain.com/docs/use_cases/agents/multi_modal_output_agent
38e7d85f58e8-3
![png](_multi_modal_output_agent_files/output_10_1.png) StableDiffusion​tools = [SteamshipImageGenerationTool(model_name="stable-diffusion")]mrkl = initialize_agent( tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)output = mrkl.run("How would you visualize a parot playing soccer?") ...
https://python.langchain.com/docs/use_cases/agents/multi_modal_output_agent
78ab88592025-0
BabyAGI with Tools | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsBabyAGI User GuideBabyAGI with ToolsCAMEL Role-Playing Autonomous Cooperat...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-2
{})Define the Chains​BabyAGI relies on three LLM chains:Task creation chain to select new tasks to add to the listTask prioritization chain to re-prioritize tasksExecution Chain to execute the tasksNOTE: in this notebook, the Execution chain will now be an agent.class TaskCreationChain(LLMChain): """Chain to gener...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-3
"result", "task_description", "incomplete_tasks", "objective", ], ) return cls(prompt=prompt, llm=llm, verbose=verbose)class TaskPrioritizationChain(LLMChain): """Chain to prioritize tasks.""" @classmethod def from_llm(cls, llm: BaseLLM, ver...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-4
template=task_prioritization_template, input_variables=["task_names", "next_task_id", "objective"], ) return cls(prompt=prompt, llm=llm, verbose=verbose)from langchain.agents import ZeroShotAgent, Tool, AgentExecutorfrom langchain import OpenAI, SerpAPIWrapper, LLMChaintodo_prompt = PromptTempl...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-5
suffix=suffix, input_variables=["objective", "task", "context", "agent_scratchpad"],)Define the BabyAGI Controller​BabyAGI composes the chains defined above in a (potentially-)infinite loop.def get_next_task( task_creation_chain: LLMChain, result: Dict, task_description: str, task_list: List[str], o...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-6
if not task_string.strip(): continue task_parts = task_string.strip().split(".", 1) if len(task_parts) == 2: task_id = task_parts[0].strip() task_name = task_parts[1].strip() prioritized_task_list.append({"task_id": task_id, "task_name": task_name}) return pr...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-7
task_prioritization_chain: TaskPrioritizationChain = Field(...) execution_chain: AgentExecutor = Field(...) task_id_counter: int = Field(1) vectorstore: VectorStore = Field(init=False) max_iterations: Optional[int] = None class Config: """Configuration for this pydantic object.""" arbitrary...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-8
return ["objective"] @property def output_keys(self) -> List[str]: return [] def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]: """Run the agent.""" objective = inputs["objective"] first_task = inputs.get("first_task", "Make a todo list") self.add_task({"task_id": 1, ...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-9
self.print_task_result(result) # Step 3: Store the result in Pinecone result_id = f"result_{task['task_id']}" self.vectorstore.add_texts( texts=[result], metadatas=[{"task": task["task_name"]}], ids=[result_id], ...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-10
for new_task in new_tasks: self.task_id_counter += 1 new_task.update({"task_id": self.task_id_counter}) self.add_task(new_task) self.task_list = deque( prioritize_tasks( self.task_prioritization_chain, ...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-11
+ "\033[0m\033[0m" ) break return {} @classmethod def from_llm( cls, llm: BaseLLM, vectorstore: VectorStore, verbose: bool = False, **kwargs ) -> "BabyAGI": """Initialize the BabyAGI Controller.""" task_creation_chain = TaskCreationChain.from_llm(llm, v...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-12
vectorstore=vectorstore, **kwargs, )Run the BabyAGI​Now it's time to create the BabyAGI controller and watch it try to accomplish your objective.OBJECTIVE = "Write a weather report for SF today"llm = OpenAI(temperature=0)# Logging of LLMChainsverbose = False# If None, will keep on going forevermax_i...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-13
Write a brief introduction to the weather report 5. Describe current weather conditions in San Francisco 6. Discuss any upcoming weather changes 7. Summarize the weather report 8. Proofread and edit the report 9. Submit the report Thought: I now know the final answer Final Answer: A weather report ...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-14
Proofread and edit the report 9: Submit the report 1: Research current weather conditions in San Francisco *****NEXT TASK***** 2: Gather data on temperature, humidity, wind speed, and other relevant weather conditions > Entering new AgentExecutor chain... Thought: I need to search for ...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-15
Today in San Francisco, the temperature is 67F with winds WNW at 10 to 15 mph. The sky is clear to partly cloudy. *****TASK LIST***** 3: Research current weather conditions in San Francisco 4: Compare the current weather conditions in San Francisco to the average for this time of year. 5: Identify a...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
78ab88592025-16
for current weather conditions in San Francisco Action: Search Action Input: Current weather conditions in San Francisco Observation: TodaySun 04/09 High 67 · 1% Precip. ; TonightSun 04/09 Low 49 · 9% Precip. ; TomorrowMon 04/10 High 64 · 11% Precip. Thought: I now know the final answer Final Answer: ...
https://python.langchain.com/docs/use_cases/agents/baby_agi_with_agent
662f0f4d7eeb-0
Page Not Found | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc...
https://python.langchain.com/docs/use_cases/agents/custom_agent_with_plugin_retrieval.html
a8e37532744b-0
image_agent | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/multi_modal/image_agent
a8e37532744b-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsMulti-modalimage_agentUse casesMulti-modal...
https://python.langchain.com/docs/use_cases/multi_modal/image_agent
a8e37532744b-2
Thought: I now have the UUID of the generated image. Final Answer: The UUID of the generated image is E28BE7C7-D105-41E0-8A5B-2CE21424DFEC. > Finished chain.def show_output(output): """Display the multi-modal output from the agent.""" UUID_PATTERN = re.compile( r"([0-9A-Za-z]{8}-[0-9A-Za-z]{4}-[0...
https://python.langchain.com/docs/use_cases/multi_modal/image_agent
a8e37532744b-3
verbose=True)output = mrkl.run("How would you visualize a parot playing soccer?")show_output(output)PreviousMeta-PromptMulti-modal outputs: Image & TextDall-EStableDiffusionCommunityDiscordTwitterGitHubPythonJS/TSMoreHomepageBlogCopyright © 2023 LangChain, Inc.
https://python.langchain.com/docs/use_cases/multi_modal/image_agent
3c6420097707-0
Summarization | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agent...
https://python.langchain.com/docs/use_cases/summarization
8dcaba1a2898-0
Autonomous (long-running) agents | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/autonomous_agents/
8dcaba1a2898-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsAutoGPTBabyAGI User GuideBabyAGI with Tool...
https://python.langchain.com/docs/use_cases/autonomous_agents/
8dcaba1a2898-2
easy switching and experimenting with multiple LLMs, usage of different vectorstores as memory, usage of LangChain's collection of tools.Baby AGI (Original Repo)​Baby AGI: a notebook implementing BabyAGI as LLM ChainsBaby AGI with Tools: building off the above notebook, this example substitutes in an agent with tools...
https://python.langchain.com/docs/use_cases/autonomous_agents/
773a59edffed-0
Page Not Found | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc...
https://python.langchain.com/docs/use_cases/autonomous_agents/aby_agi.html
769b9669ebc0-0
BabyAGI User Guide | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi
769b9669ebc0-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsAutoGPTBabyAGI User GuideBabyAGI with Tool...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi
769b9669ebc0-2
Initialize the vectorstore as emptyimport faissembedding_size = 1536index = faiss.IndexFlatL2(embedding_size)vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})Run the BabyAGI​Now it's time to create the BabyAGI controller and watch it try to accomplish your objective.OBJECTIVE = "Write...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi
769b9669ebc0-3
Check for any weather alerts or warnings in San Francisco 6: Check the forecast for the next 24 hours in San Francisco 7: Check the forecast for the next 48 hours in San Francisco 8: Check the forecast for the next 72 hours in San Francisco 9: Check the forecast for the next week in San Francisco 10: Che...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi
769b9669ebc0-4
11: Write a weather report for SF today. *****NEXT TASK***** 3: Check the current UV index in San Francisco. *****TASK RESULT***** The current UV index in San Francisco is moderate. The UV index is expected to remain at moderate levels throughout the day. It is recommended to wear su...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi
2d6d3bc3f282-0
marathon_times | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsAutoGPTBabyAGI User GuideBabyAGI with Tool...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-2
pushd(new_dir): """Context manager for changing the current working directory.""" prev_dir = os.getcwd() os.chdir(new_dir) try: yield finally: os.chdir(prev_dir)@tooldef process_csv( csv_file_path: str, instructions: str, output_path: Optional[str] = None) -> str: """Process a CSV by ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-3
def async_load_playwright(url: str) -> str: """Load the specified URLs using Playwright and parse using BeautifulSoup.""" from bs4 import BeautifulSoup from playwright.async_api import async_playwright results = "" async with async_playwright() as p: browser = await p.chromium.launch(headless=True...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-4
browse_web_page(url: str) -> str: """Verbose way to scrape a whole webpage. Likely to cause issues parsing.""" return run_async(async_load_playwright(url))Q&A Over a webpageHelp the model ask more directed questions of web pages to avoid cluttering its memoryfrom langchain.tools import BaseTool, DuckDuckGoSearchR...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-5
results = [] # TODO: Handle this with a MapReduceChain for i in range(0, len(web_docs), 4): input_docs = web_docs[i : i + 4] window_result = self.qa_chain( {"input_documents": input_docs, "question": question}, return_only_outputs=True, ) ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-6
import OpenAIEmbeddingsfrom langchain.tools.human.tool import HumanInputRunembeddings_model = OpenAIEmbeddings()embedding_size = 1536index = faiss.IndexFlatL2(embedding_size)vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})Setup model and AutoGPT​Model set-up# !pip install duckduckgo_...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-7
{ "text": "I need to find the winning Boston Marathon times for the past 5 years. I can use the DuckDuckGo Search command to search for this information.", "reasoning": "Using DuckDuckGo Search will help me gather information on the winning times without complications.", "plan": "- Use ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-8
past 5 years.", "reasoning": "The query_webpage command may give me more accurate and comprehensive results compared to the search command.", "plan": "- Use query_webpage command to find the winning Boston Marathon times\n- Generate a table with the year, name, country of origin, and times\n- Ensu...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-9
"plan": "- Use query_webpage command to find the winning Boston Marathon times\\n- Generate a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications", "criticism": "I may face difficulty in finding the right webpage with the desired information.", "spea...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-10
"plan": "- Write the marathon data to a CSV file\n- Process the CSV file to display the table", "criticism": "None", "speak": "I will generate a table with the year, name, country of origin, and times for the winning Boston Marathon times for the past 5 years." }, "command": { ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-11
clear and accessible format.", "plan": "- Write the data to a CSV file\n- Process the CSV file to generate the table\n- Complete the task", "criticism": "None", "speak": "I will generate a table with the year, name, country of origin, and winning times using the recently retrieved data....
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-12
"reasoning": "Generating a table will help organize the information in a structured format.", "plan": "- Create a table with the year, name, country of origin, and times\n- Ensure there are no legal complications", "criticism": "None", "speak": "I will generate a table with the winning ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-13
"reasoning": "I have already written the data to a file named 'winning_times.csv'. Now, I need to process this CSV file to properly display the data as a table.", "plan": "- Use the process_csv command to read the 'winning_times.csv' file and generate the table", "criticism": "None", "s...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-14
Year Name Country Time 0 2022 Evans Chebet Kenya 2:06:51 1 2021 Benson Kipruto Kenya 2:09:51 2 2020 Canceled due to COVID-19 pandemic NaN NaN 3 2019 Lawrence Cherono Kenya 2:07:57 4 2018 ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-15
Evans Chebet Kenya 2:06:51 1 2021 Benson Kipruto Kenya 2:09:51 2 2020 Canceled due to COVID-19 pandemic NaN NaN 3 2019 Lawrence Cherono Kenya 2:07:57 4 2018 Yuki Kawauchi Japan 2:15:58 > Finished chain. { "...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-16
"speak": "I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years." }, "command": { "name": "process_csv", "args": { "csv_file_path": "winning_times.csv", "instructions": "Read the CSV ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-17
pandemic NaN NaN 3 2019 Lawrence Cherono Kenya 2:07:57 4 2018 Yuki Kawauchi Japan 2:15:58 Thought:I now know the final answer. Final Answer: Year Name Country Time 0 2022 Evans Chebet ...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
2d6d3bc3f282-18
"thoughts": { "text": "I have already generated a table with the winning Boston Marathon times for the past 5 years. Now, I can finish the task.", "reasoning": "I have completed the required actions and obtained the desired data. The task is complete.", "plan": "- Use the finish command...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times
13811030488d-0
BabyAGI with Tools | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsAutoGPTBabyAGI User GuideBabyAGI with Tool...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-2
= FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})Define the Chains​BabyAGI relies on three LLM chains:Task creation chain to select new tasks to add to the listTask prioritization chain to re-prioritize tasksExecution Chain to execute the tasksNOTE: in this notebook, the Execution chain will now ...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-3
tools, prefix=prefix, suffix=suffix, input_variables=["objective", "task", "context", "agent_scratchpad"],)llm = OpenAI(temperature=0)llm_chain = LLMChain(llm=llm, prompt=prompt)tool_names = [tool.name for tool in tools]agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)agent_executor = AgentE...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-4
humidity, wind speed, and other relevant weather conditions 3. Analyze data to determine current weather trends 4. Write a brief introduction to the weather report 5. Describe current weather conditions in San Francisco 6. Discuss any upcoming weather changes 7. Summarize the weather report 8. Proofre...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-5
2: Gather data on precipitation, cloud cover, and other relevant weather conditions; 3: Analyze data to determine any upcoming weather changes; 4: Research current weather forecasts for San Francisco; 5: Create a visual representation of the weather report; 6: Include relevant images and graphics in the rep...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-6
5. Compile the data into a report format. 6. Proofread the report for accuracy and clarity. 7. Publish the report to a website or other platform. 8. Distribute the report to relevant stakeholders. I now know the final answer Final Answer: Today in San Francisco, the temperature is 46 degrees Fah...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-7
Include a summary of the potential trends in the weather data; 16: Include a summary of the data sources used in the report; 17: Analyze data to determine any upcoming weather changes; 18: Research current weather forecasts for San Francisco; 19: Create a visual representation of the weather report; 20: ...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
13811030488d-8
avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreadin...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent
57917758916b-0
Page Not Found | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc...
https://python.langchain.com/docs/use_cases/autonomous_agents/autogpt.html
e78f66cd675b-0
Page Not Found | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc...
https://python.langchain.com/docs/use_cases/autonomous_agents/marathon_times.html
0ff7172d6655-0
Page Not Found | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc...
https://python.langchain.com/docs/use_cases/autonomous_agents/baby_agi_with_agent.html
050109eaccdc-0
Page Not Found | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc...
https://python.langchain.com/docs/use_cases/autonomous_agents/hugginggpt.html
1ed02a22bc52-0
Meta-Prompt | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsAutoGPTBabyAGI User GuideBabyAGI with Tool...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-2
important details in the current Instructions! Indicate the new Instructions by "Instructions: ...".Repeat.The only fixed instructions for this system (which I call Meta-prompt) is the meta-prompt that governs revision of the agent’s instructions. The agent has no memory between episodes except for the instruction it...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-3
the Instructions so that Assistant would quickly and correctly respond in the future. #### {chat_history} #### Please reflect on these interactions. You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there thin...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-4
= [success_phrase, failed_phrase] instructions = "None" for i in range(max_meta_iters): print(f"[Episode {i+1}/{max_meta_iters}]") chain = initialize_chain(instructions, memory=None) output = chain.predict(human_input=task) for j in range(max_iters): print(f"(Step {j+1}/{max...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-5
80 + "\n") print(f"You failed! Thanks for playing!")Specify a task and interact with the agent​task = "Provide a systematic argument for why we should always eat pasta with olives."main(task) [Episode 1/5] > Entering new LLMChain chain... Prompt after formatting: Instructions: None ...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-6
provide a unique flavor that can help to make the dish more interesting and enjoyable. Human: You response is not in the form of a poem. Try again! Assistant: > Finished chain. (Step 2/3) Assistant: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a gre...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-7
to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal. Human: Your response is not piratey enough. Try a...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-8
the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. Human: You response is not in the form of a poem. Try again! AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of he...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-9
will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by "Instructions: ...". > Finished chain. Feedback: Critique: The Assistant s...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-10
be sure to please. The briny taste be sure to tantalize yer taste buds with ease. Second, the olives add a bit of texture to the dish. The crunchy bites be sure to make yer mouth water with a wish. Third, the olives add a bit of color to the plate. The vibrant green be sure to make yer eyes appre...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-11
the plate. The vibrant green be sure to make yer eyes appreciate. So, me hearties, ye should always eat pasta with olives. The flavor, texture, and color be sure to make yer meal a success! Human: Your response is too long! Try again. Assistant: > Finished chain. (Step 2/3) Assis...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
1ed02a22bc52-12
with a wish. Third, the olives add a bit of color to the plate. The vibrant green be sure to make yer eyes appreciate. So, me hearties, ye should always eat pasta with olives. The flavor, texture, and color be sure to make yer meal a success! Human: Your response is too long! Try again. AI: ...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt
c7ffaa090357-0
Page Not Found | 🦜�🔗 Langchain Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc...
https://python.langchain.com/docs/use_cases/autonomous_agents/meta_prompt.html
2561e4b381ba-0
HuggingGPT | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/autonomous_agents/hugginggpt
2561e4b381ba-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsAutoGPTBabyAGI User GuideBabyAGI with Tool...
https://python.langchain.com/docs/use_cases/autonomous_agents/hugginggpt
2561e4b381ba-2
"translation", "huggingface-tools/text-to-image", "huggingface-tools/text-to-video", "text-to-speech", "huggingface-tools/text-download", "huggingface-tools/image-transformation", ]]Setup model and HuggingGPT​We create an instance of HuggingGPT and use ChatGPT as the controller t...
https://python.langchain.com/docs/use_cases/autonomous_agents/hugginggpt
1f8fc1cf66ec-0
AutoGPT | 🦜�🔗 Langchain
https://python.langchain.com/docs/use_cases/autonomous_agents/autogpt
1f8fc1cf66ec-1
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsAutoGPTBabyAGI User GuideBabyAGI with Tool...
https://python.langchain.com/docs/use_cases/autonomous_agents/autogpt
1f8fc1cf66ec-2
= 1536index = faiss.IndexFlatL2(embedding_size)vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})Setup model and AutoGPT​Initialize everything! We will use ChatOpenAI modelfrom langchain.experimental import AutoGPTfrom langchain.chat_models import ChatOpenAIagent = AutoGPT.from_llm_and...
https://python.langchain.com/docs/use_cases/autonomous_agents/autogpt