From a45c82aa1aa3938942be863a65af66782025c000 Mon Sep 17 00:00:00 2001 From: Jeff Tang Date: Tue, 10 Dec 2024 19:20:22 -0800 Subject: [PATCH] llama stack port completed; README update --- docs/zero_to_hero_guide/gmail_agent/README.md | 266 ++++++++++++++++++ .../gmail_agent/functions_prompt.py | 32 +-- .../zero_to_hero_guide/gmail_agent/gmagent.py | 145 +--------- docs/zero_to_hero_guide/gmail_agent/main.py | 59 ++-- .../gmail_agent/requirements.txt | 3 +- 5 files changed, 320 insertions(+), 185 deletions(-) create mode 100644 docs/zero_to_hero_guide/gmail_agent/README.md diff --git a/docs/zero_to_hero_guide/gmail_agent/README.md b/docs/zero_to_hero_guide/gmail_agent/README.md new file mode 100644 index 000000000..a70b037cd --- /dev/null +++ b/docs/zero_to_hero_guide/gmail_agent/README.md @@ -0,0 +1,266 @@ +# Emagent - A Llama and Llama Stack Powered Email Agent + +This is a Llama Stack port of the [Emagent](https://github.com/meta-llama/llama-recipes/tree/gmagent/recipes/use_cases/email_agent) app that shows how to build an email agent app powered by Llama 3.1 8B and Llama Stack, using Llama Stack custom tool and agent APIs. The end goal is to cover all components of a production-ready agent app, acting as an assistant to your email, with great user experience: intuitive, engaging, efficient and reliable. We'll use Gmail as an example but any email client API's can be used instead. + +Currently implemented features of Emagent include: +* search for emails and attachments +* get email detail +* reply to a specific email +* forward an email +* get summary of a PDF attachment +* draft and send an email + +If your main intent is to know the difference between using Llama Stack APIs or not for this agent implementation, go to [Implementation Notes](#implementation-notes). + +# Overview + +Email is an essential and one top killer app people use every day. A recent [State of AI Agents](https://www.langchain.com/stateofaiagents) survey by LangChain finds that "The top use cases for agents include performing research and summarization (58%), followed by streamlining tasks for personal productivity or assistance (53.5%)." + +Andrew Ng wrote a 5-part [Agentic Design Patterns](https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/) in March 2024 predicting "AI agent workflows will drive massive AI progress this year". + +Deloitte published in November 2024 a report on [AI agents and multiagent systems](https://www2.deloitte.com/content/dam/Deloitte/us/Documents/consulting/us-ai-institute-generative-ai-agents-multiagent-systems.pdf) stating that "Through their ability to reason, plan, remember and act, AI agents address key limitations of typical language models." and "Executive leaders should make moves now to prepare for and embrace this next era of intelligent organizational transformation." + +In the Thanksgiving week, a new startup [/dev/agent](https://sdsa.ai/) building the next-gen OS for AI agents was in the spotlight. + +In December, Sequoia posted [here](https://www.linkedin.com/posts/konstantinebuhler_the-ai-landscape-is-shifting-from-simple-activity-7270111755710672897-ZHnr/) saying 2024 has been the year of agents (an agent is an AI that can complete tasks, not only tells you how to do it but also does it for you directly), and 2025 will be the year of networks of AI agents. + +So what exactly is an AI agent and how to start building an agent app? + +## What is an agent? + +The concept of agent is not new - in the 2010 3rd edition of Russell and Norvig's classic book Artificial Intelligence: A Modern Approach ("Modern" by 2010, two years before the deep learning revolution that started the truly modern AI), an agent is defined as "anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators". These days, AI agent basically means LLM-powered agent - well, if we treat natural language understanding as a type of sensor, LLM agent is still a sub-category of the traditional agent. + +Lilian Weng in her popular June 2023 blog [LLM Powered Autonomous Agents](https://lilianweng.github.io/posts/2023-06-23-agent/) defines LLM-powered agent system to have four key components: + * Planning and Reflection: can break down large tasks into smaller ones; can do self-reflection over past actions and self improve; + * Memory: can use contextual info and recall info over extended periods (for other components to use); + * Tool Use: can understand what external APIs to use for info or action not built into LLMs; + * Action: can actually run the tools. + +Andrew Ng describes four [agentic design patterns](https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/) as: +* Reflection +* Planning +* Tool calling +* Multi-agent collaboration, where "memory" is mentioned: Each agent implements its own workflow, has its own memory (itself a rapidly evolving area in agentic technology: how can an agent remember enough of its past interactions to perform better on upcoming ones?) + +In Deloitte's [report](https://www2.deloitte.com/content/dam/Deloitte/us/Documents/consulting/us-ai-institute-generative-ai-agents-multiagent-systems.pdf), AI agents are reasoning engines that can understand context, plan workflows, connect to external tools and data, and execute actions to achieve a defined goal. + +In a November 2024 blog by Letta [The AI agents stack](https://www.letta.com/blog/ai-agents-stack), LLM powered agent is described as the combination of tools use, autonomous execution, and memory. + +In addition, Harrison Chase defines agent in the blog [What is an AI agent](https://blog.langchain.dev/what-is-an-agent/) as "a system that uses an LLM to decide the control flow of an application." + +Yet another simple [summary](https://www.felicis.com/insight/the-agentic-web) by Felicis of what an agent does is that an agent expands LLMs to go from chat to act: an agent can pair LLMs with external data, multi-step reasoning and planning, and act on the user's behalf. + +All in all (see [Resources](#resources) for even more info), agents are systems that take a high-level task, use an LLM as a reasoning and planning engine, with the help of contextual info and long-term memory if needed, to decide what actions to take, reflect and improve on the actions, and eventually execute those actions to accomplish the task. + +It's time to see an agent app in action and enjoy some coding. Below is a preview of the questions or requests one may ask Gmagent: + +# Example Asks to Gmagent + +* do i have emails with attachment larger than 5mb? +* what's the detail of the email with subject this is an interesting paper +* how many emails with attachment +* tell me the detail about the attachments for the email with subject papers to read? +* give me a summary of the pdf thinking_llm.pdf +* draft an email to jeffxtang@meta.com saying how about lunch together this thursday? +* send the draft + +# Setup and Installation + +If you feel intimated by the steps of the following Enable Gmail API section, you may want to check again the example asks (to see what you can ask to the agent) and the example log (to see the whole conversation with gmagent) - the devil's in the detail and all the glorious description of a powerful trendy agent may not mention the little details one has to deal with to build it. + +## Enable Gmail API +1. Go to the [Google Cloud Console](https://console.cloud.google.com/). +2. Create a new project by clicking the dropdown on the top left then click NEW PROJECT. +3. Enter a Project name then click CREATE. +4. Under "APIs & Services" > "Enabled APIs & services", search for "gmail" and then Enable the "Gmail API" for your project. +5. Under "APIs & Services" > "OAuth consent screen", click "GO TO NEW EXPERIENCE", then click "GET STARTED", enter App name, select your gmail as User support email, choose External under Audience, enter your gmail again as Contact Information, and finally check the I agree to the Google API Services under Finish and click Continue - Create. +5. Again under "APIs & Services", go to Credentials. Click on + CREATE CREDENTIALS, then choose OAuth client ID (NOT API key). +Select Desktop App (NOT Web application, because you're assumed to want to start your Gmail agent locally first) as the application type and name it. Click Create to generate your client ID and client secret. +6. Click Download JSON and rename the downloaded file as credentials.json. This file will be used in your Python script for authentication. + +## Install Ollama with Llama 3.1 8B + +Download Ollama (available for macOS, Linux, and Windows) [here](https://ollama.com/). Then download and test run the Llama 3.1 8B model by running on a Terminal: +``` +ollama run llama3.1 +``` + +This will download a quantized version of Llama 3.1 of the size 4.7GB. + +## Install required packages +First, create a Conda or virtual env: + +``` +conda create -n emagent python=3.10 +conda activate emagent +``` +or +``` +python -m venv emagent +source emagent/bin/activate # on Linux, macOS: +source emagent\Scripts\activate # on Windows +``` + +Then install the required Python libraries: +``` +git clone https://github.com/meta-llama/llama-stack +cd llama-stack/docs/zero_to_hero_guide/email_agent +pip install -r requirements.txt +``` + +# Run Emagent + +To run Emagent, you need to first copy the `credentials.json` file downloaded and renamed above in Step 6 of Enable Gmail API to the email_agent folder, then run: +``` +python main.py --gmail +``` + +The first time you run it, you'll get a prompt like this; +``` +Please visit this URL to authorize this application: https://accounts.google.com/o/oauth2/auth?response_type=code&client_id=xxxx +Enter the authorization code: +``` + +You need to copy the URL above and open it in a browser - if you Sign in with Google using the same Gmail you enabled for the Gmail API, then you'll see "You’ve been given access to an app that’s currently being tested. You should only continue if you know the developer that invited you.", otherwise if you sign in with another Gmail, you'll see "Gmail Agent App has not completed the Google verification process. The app is currently being tested, and can only be accessed by developer-approved testers. If you think you should have access, contact the developer." + +In the latter case, go to APIs & Services > OAuth consent screen > Test users, and click the + ADD USERS button, and you'll see this message: While publishing status is set to "Testing", only test users are able to access the app. Allowed user cap prior to app verification is 100, and is counted over the entire lifetime of the app. + +After clicking Continue, check the Select all checkbox to enable both settings required for running Gmagent: +``` +View your email messages and settings. +Manage drafts and send emails. +``` + +Finally, copy the Authorization code and paste it to the Terminal, hit Enter and you'll see Gmagent's initial greeting (which will likely differ because the default temperature value 0.8 is used here - see [Ollama's model file](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values) for detail) such as: +``` +Hello! I'm Gmagent, here to help you manage your Gmail account with ease. + +What would you like to do today? Do you want me to: + +Check and respond to new emails +Compose a new email +Organize your inbox with filters or labels +Delete unwanted emails +Something else? + +Let me know how I can assist you! + +Your ask: +``` + +If you cancel here and run the command `python main.py --gmail ` again you should see the Gmagent greeting right away without the need to enter an authorization code, unless you enter a different Gmail address for the first time - in fact, for each authorized (added as a test user) Gmail address, a file `token_xxxx@gmail.com.pickle` will be created which contains the authorized token. + +See the example asks and interaction log above for the types of asks you may enter. + +# Implementation Notes +Notes here mainly cover how custom functions are defined, how Gmail API based functions are implemented, and how an Agent class is defined to handle memory for contextual chat and perform pre- and post-processing on the tool calling. + +## Available Custom Tool Definition +The `functions_prompt.py` defines the following six custom tools (functions), each as a subclass of Llama Stack's `CustomTool`, along with examples for each function call spec that Llama should return): + +* ListEmailsTool +* GetEmailDetailTool +* SendEmailTool +* GetPDFSummaryTool +* CreateDraftTool +* SendDraftTool + + +Below is an example custom tool call spec in JSON format, for the user asks such as "do i have emails with attachments larger than 5mb", "any attachments larger than 5mb" or "let me know if i have large attachments over 5mb": +``` +{"name": "list_emails", "parameters": {"query": "has:attachment larger:5mb"}} +``` + +Porting the custom function definition to Llama Stack's CustomTool subclass is straightforward. + +## Actual Function Call Implementation + +For each defined custom function call, its implementation using the Gmail API is present in `gmagent.py`. And we simply call them in each of the CustomTool subclass's `run_impl` method. For example, the `list_emails` is defined as follows: + +``` +def list_emails(query='', max_results=100): + emails = [] + next_page_token = None + + while True: + response = service.users().messages().list( + userId=user_id, + maxResults=max_results, + pageToken=next_page_token, + q=query + ).execute() + + if 'messages' in response: + for msg in response['messages']: + sender, subject, received_time = get_email_info(msg['id']) + emails.append( + { + "message_id": msg['id'], + "sender": sender, + "subject": subject, + "received_time": received_time + } + ) + + next_page_token = response.get('nextPageToken') + + if not next_page_token: + break + + return emails +``` + +The function will be called by the Llama Stack agent in the `run_impl` method of the `ListEmailsTool` class if a user ask is like "do i have emails with attachments larger than 5mb": +``` +emails = list_emails(query) + ``` + +## The Llama Stack Agent class + +The `create_gmail_agent` in main.py creates a Llama Stack Agent with 6 custom tools using a `LlamaStackClient` instance that connects to Together.ai's Llama Stack server. The agent then creates a session, and in a loop, for each user ask, the agent uses the same session to create a turn, inside which a tool call spec is generated based on the user's ask and actual tool call then happens. After post-processing of the tool call result, a user-friendly message is printed to respond to the user's original ask. + +When you try out Emagent, you'll likely find that further pre- and post-processing still needed to make it production ready. In a great video on [Vertical LLM Agents](https://www.youtube.com/watch?v=eBVi_sLaYsc), Jake Heller said "after passes frankly even like 100 tests the odds that it will do on any random distribution of user inputs of the next 100,000, 100% accurately is very high" and "by the time you've dealt with like all the edge cases... there might be dozens of things you build into your application to actually make it work well and then you get to the prompting piece and writing out tests and very specific prompts and the strategy for how you break down a big problem into step by step by step thinking and how you feed in the information how you format that information the right way". That's what all the business logic is about. We'll cover decomposing a complicated ask and multi-step reasoning in a future version of Gmagent, and continue to explore the best possible way to streamline the pre- and post-processing. + +## Debugging output + +When running Gmagent, the detailed Llama returns, pre-processed tool call specs and the actual tool calling results are inside the `-------------------------` block, e.g.: + +------------------------- +Calling Llama... + +Llama returned: {'function_name': 'list_emails', 'parameters': {'query': 'subject:papers to read has:attachment'}}. + +Calling tool to access Gmail API: list_emails, {'query': 'subject:papers to read has:attachment'}... + +Tool calling returned: [{'message_id': '1936ef72ad3f30e8', 'sender': 'gmagent_tester1@gmail.com', 'subject': 'Fwd: papers to read', 'received_time': '2024-11-27 10:51:51 PST'}, {'message_id': '1936b819706a4923', 'sender': 'Jeff Tang ', 'subject': 'papers to read', 'received_time': '2024-11-26 18:44:19 PST'}] + +------------------------- + + +# TODOs + +1. Improve the search, reply, forward, create email draft, and query about types of attachments. +2. Improve the fallback and error handling mechanism when the user asks don't lead to a correct function calling spec or the function calling fails. +3. Improve the user experience by showing progress when some Gmail search API calls take long (minutes) to complete. +4. Implement the async behavior of Gmagent - schedule an email to be sent later. +5. Implement the agent planning - decomposing a complicated ask into sub-tasks, using ReAct and other methods. +6. Implement the agent long-term memory - longer context and memory across sessions (consider using Llama Stack/MemGPT/Letta) +7. Implement reflection - on the tool calling spec and results. +8. Introduce multiple-agent collaboration. +9. Implement the agent observability. +10. Compare different agent frameworks using Gmagent as the case study. +11. Add and implement a test plan and productionize Gmagent. + + +# Resources +1. Lilian Weng's blog [LLM Powered Autonomous Agents](https://lilianweng.github.io/posts/2023-06-23-agent/) +2. Andrew Ng's posts [Agentic Design Patterns](https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/) with basic [implementations from scratch](https://github.com/neural-maze/agentic_patterns). +3. LangChain's survey [State of AI Agents](https://www.langchain.com/stateofaiagents) +4. Deloitte's report [AI agents and multiagent systems](https://www2.deloitte.com/content/dam/Deloitte/us/Documents/consulting/us-ai-institute-generative-ai-agents-multiagent-systems.pdf) +5. Letta's blog [The AI agents stack](https://www.letta.com/blog/ai-agents-stack) +6. Microsoft's multi-agent system [Magentic-One](https://www.microsoft.com/en-us/research/articles/magentic-one-a-generalist-multi-agent-system-for-solving-complex-tasks) +7. Amazon's [Multi-Agent Orchestrator framework](https://awslabs.github.io/multi-agent-orchestrator/) +8. Deeplearning.ai's [agent related courses](https://www.deeplearning.ai/courses/?courses_date_desc%5Bquery%5D=agents) (Meta, AWS, Microsoft, LangChain, LlamaIndex, crewAI, AutoGen, Letta) and some [lessons ported to using Llama](https://github.com/meta-llama/llama-recipes/tree/main/recipes/quickstart/agents/DeepLearningai_Course_Notebooks). +9. Felicis's [The Agentic Web](https://www.felicis.com/insight/the-agentic-web) +10. A pretty complete [list of AI agents](https://github.com/e2b-dev/awesome-ai-agents), not including [/dev/agents](https://sdsa.ai/), a very new startup building the next-gen OS for AI agents, though. +11. Sequoia's [post](https://www.linkedin.com/posts/konstantinebuhler_the-ai-landscape-is-shifting-from-simple-activity-7270111755710672897-ZHnr/) on 2024 being the year of AI agents and 2025 networks of AI agents. diff --git a/docs/zero_to_hero_guide/gmail_agent/functions_prompt.py b/docs/zero_to_hero_guide/gmail_agent/functions_prompt.py index e9cbfb88a..3e974a1f2 100644 --- a/docs/zero_to_hero_guide/gmail_agent/functions_prompt.py +++ b/docs/zero_to_hero_guide/gmail_agent/functions_prompt.py @@ -160,11 +160,11 @@ class SendEmailTool(CustomTool): ) return [message] - async def run_impl(self, query: str, maxResults: int = 100) -> Dict[str, Any]: - """Query to get a list of emails matching the query.""" + async def run_impl(self, action, to, subject, body="", email_id="") -> Dict[str, Any]: + """Send an email.""" - emails = [] - return emails + result = send_email(action, to, subject, body, email_id) + return {"name": self.get_name(), "result": result} class GetPDFSummaryTool(CustomTool): @@ -205,11 +205,11 @@ class GetPDFSummaryTool(CustomTool): ) return [message] - async def run_impl(self, query: str, maxResults: int = 100) -> Dict[str, Any]: - """Query to get a list of emails matching the query.""" + async def run_impl(self, file_name: str) -> Dict[str, Any]: + """Get the summary of a PDF file.""" - emails = [] - return emails + summary = get_pdf_summary(file_name) + return {"name": self.get_name(), "result": summary} class CreateDraftTool(CustomTool): @@ -270,11 +270,11 @@ class CreateDraftTool(CustomTool): ) return [message] - async def run_impl(self, query: str, maxResults: int = 100) -> Dict[str, Any]: - """Query to get a list of emails matching the query.""" + async def run_impl(self, action, to, subject, body="", email_id="") -> Dict[str, Any]: + """Create an email draft.""" - emails = [] - return emails + result = create_draft(action, to, subject, body, email_id) + return {"name": self.get_name(), "result": result} class SendDraftTool(CustomTool): @@ -315,11 +315,11 @@ class SendDraftTool(CustomTool): ) return [message] - async def run_impl(self, query: str, maxResults: int = 100) -> Dict[str, Any]: - """Query to get a list of emails matching the query.""" + async def run_impl(self, id: str) -> Dict[str, Any]: + """Send the last draft email.""" - emails = [] - return emails + result = send_draft(memory['draft_id']) + return {"name": self.get_name(), "result": result} examples = """ diff --git a/docs/zero_to_hero_guide/gmail_agent/gmagent.py b/docs/zero_to_hero_guide/gmail_agent/gmagent.py index 45ab78a05..0b55aa14e 100644 --- a/docs/zero_to_hero_guide/gmail_agent/gmagent.py +++ b/docs/zero_to_hero_guide/gmail_agent/gmagent.py @@ -18,6 +18,9 @@ from pathlib import Path from shared import memory SCOPES = ['https://www.googleapis.com/auth/gmail.readonly', 'https://www.googleapis.com/auth/gmail.compose'] +user_email = None +service = None +user_id = 'me' def authenticate_gmail(user_email): creds = None @@ -44,7 +47,6 @@ def authenticate_gmail(user_email): service = build('gmail', 'v1', credentials=creds) return service - def num_of_emails(query=''): response = service.users().messages().list( userId='me', @@ -52,7 +54,6 @@ def num_of_emails(query=''): maxResults=1).execute() return response.get('resultSizeEstimate', 0) - def list_emails(query='', max_results=100): emails = [] next_page_token = None @@ -108,12 +109,10 @@ def get_email_detail(detail, which): else: message_id = memory['emails'][-1]['message_id'] - if detail == 'body': return get_email_body(message_id) elif detail == 'attachment': - return get_email_attachments(which) - + return get_email_attachments(message_id) def get_email_body(message_id): try: @@ -147,7 +146,6 @@ def get_email_body(message_id): print(f"An error occurred: {e}") return None - def parse_message(message): payload = message['payload'] headers = payload.get("headers") @@ -184,8 +182,7 @@ def parse_message(message): # Single part message data = payload['body']['data'] body = base64.urlsafe_b64decode(data).decode('utf-8') - return sender, subject, received_time, body - + return sender, subject, received_time, body def get_email_info(msg_id): message = service.users().messages().get( @@ -197,7 +194,6 @@ def get_email_info(msg_id): return sender, subject, received_time - def reply_email(message_id, reply_text): # Fetch the original message original_message = service.users().messages().get( @@ -235,7 +231,6 @@ def reply_email(message_id, reply_text): body=body).execute() print("Reply sent. Message ID:", sent_message['id']) - def forward_email(message_id, forward_to, email_body=None): """ Forwards an email, preserving the original MIME type, including multipart/related. @@ -326,7 +321,6 @@ def forward_email(message_id, forward_to, email_body=None): print(f"Message forwarded successfully! Message ID: {sent_message['id']}") - def send_email(action, to, subject, body="", email_id=""): if action == "compose": message = MIMEText(body) @@ -346,7 +340,6 @@ def send_email(action, to, subject, body="", email_id=""): elif action == "forward": forward_email(email_id, to, body) - def create_draft(action, to, subject, body="", email_id=""): if action == "new": message = MIMEText(body) @@ -368,8 +361,6 @@ def create_draft(action, to, subject, body="", email_id=""): else: return - - def create_reply_draft(message_id, reply_text): # Fetch the original message original_message = service.users().messages().get( @@ -403,7 +394,6 @@ def create_reply_draft(message_id, reply_text): draft = service.users().drafts().create(userId=user_id, body=draft_body).execute() return draft['id'] - def create_forward_draft(message_id, recipient_email, custom_message=None): # Get the original message original_message = service.users().messages().get( @@ -430,14 +420,12 @@ def create_forward_draft(message_id, recipient_email, custom_message=None): print(f"Forward draft created with ID: {draft['id']}") return draft['id'] - def send_draft(id): sent_message = service.users().drafts().send( userId=user_id, body={'id': id} ).execute() return f"Draft sent with email ID: {sent_message['id']}" - def get_pdf_summary(file_name): text = pdf2text(file_name) @@ -445,7 +433,6 @@ def get_pdf_summary(file_name): response = llama31(text, "Generate a summary of the input text in 5 sentences.") return response - def get_email_attachments(message_id, mime_type='application/pdf'): attachments = [] @@ -496,7 +483,6 @@ def get_email_attachments(message_id, mime_type='application/pdf'): rslt += f"{a['filename']} - {a['size']} bytes\n" return rslt #attachments - def pdf2text(file): text = '' try: @@ -510,11 +496,6 @@ def pdf2text(file): return text - -user_email = None -service = None -user_id = 'me' - def set_email_service(gmail): global user_email global service @@ -522,122 +503,6 @@ def set_email_service(gmail): user_email = gmail service = authenticate_gmail(user_email) -# class Agent: -# def __init__(self, system_prompt=""): -# self.system_prompt = system_prompt -# self.messages = [] -# -# # Gmagent-specific short term memory, used to answer follow up questions AFTER a list of emails is found matching user's query -# self.emails = [] -# self.draft_id = None -# -# if self.system_prompt: -# self.messages.append({"role": "system", "content": system_prompt}) -# -# def __call__(self, user_prompt_or_tool_result, is_tool_call=False): -# # if it's tool call result, use "ipython" instead of "user" for the role -# self.messages.append({"role": ("ipython" if is_tool_call else "user"), "content": user_prompt_or_tool_result}) -# result = self.llama() -# print(f"\nLlama returned: {result}.") -# if type(result) == dict: # result is a dict only if it's a tool call spec -# function_name = result["function_name"] -# func = globals()[function_name] -# parameters = result["parameters"] -# if function_name == "get_email_detail": -# # TODO: parse which - valid values are first, second, -# # third, fourth, last, from xxx -# if 'id' in parameters.keys(): -# parameters['which'] = parameters['id'] -# del parameters['id'] # per the function spec -# elif 'which' in parameters.keys(): -# if 'from ' in parameters['which']: -# sender = parameters['which'].split('from ')[-1] -# for email in self.emails: -# if email['sender'].find(sender) != -1: -# parameters['which'] = email['message_id'] -# break -# if 'subject ' in parameters['which']: -# subject = parameters['which'].split('subject ')[-1] -# # exact match beats substring -# for email in self.emails: -# if email['subject'].upper() == subject.upper(): -# parameters['which'] = email['message_id'] -# break -# elif email['subject'].upper().find(subject.upper()) != -1: -# parameters['which'] = email['message_id'] -# -# elif 'id_' in parameters['which']: -# parameters['which'] = parameters['which'].split('id_')[-1] -# else: -# parameters['which'] = self.emails[-1]['message_id'] -# elif function_name == "send_draft": -# parameters['id'] = self.draft_id -# -# print(f"\nCalling tool to access Gmail API: {function_name}, {parameters}...") -# result = func(**parameters) -# print(f"\nTool calling returned: {result}") -# -# # convert function calling result to concise summary, offering interactive follow ups, -# # for smooth and user friendly experience -# if function_name == 'list_emails': -# self.emails = result -# num = len(result) -# if num == 0: -# output = "I couldn't find any such emails. What else would you like to do?" -# elif num <= 5: -# output = f"I found {num} email{'s' if num > 1 else ''} matching your query:\n" -# for i, email in enumerate(result, start=1): -# output += f"{i}. From: {email['sender']}, Subject: {email['subject']}, Received on: {email['received_time']}\n" -# else: -# output = f"I found {num} emails matching your query. Here are the first 5 emails:\n" -# for i in range(1, 6): -# output += f"{i}. From: {result[i-1]['sender']}, Subject: {result[i-1]['subject']}, Received on: {result[i-1]['received_time']}\n" -# elif function_name == "get_email_detail": -# output = result -# elif function_name == "get_pdf_summary": -# output = result -# elif function_name == "send_email": -# output = "Email sent." -# elif function_name == "create_draft": -# output = "Draft created." -# self.draft_id = result -# elif function_name == "send_draft": -# output = result -# -# print(f"\n-------------------------\n\nGmagent: {output}\n") -# else: -# output = result # direct text, not JSON, response by Llama -# -# # adding this may cause Llama to hallucinate when answering -# # follow up questions. e.g. "do i have emails with attachments -# # larger than 20mb" got right tool calling response, then -# # follow up "larger than 10mb" got hallucinated response. -# # self.messages.append({"role": "assistant", "content": output}) -# -# # this mitigates the hallucination -# self.messages.append({"role": "assistant", "content": str(result)}) -# -# return output -# -# def llama(self): -# response = ollama.chat(model='llama3.1', -# messages = self.messages, -# options = { -# "temperature": 0.0 -# } -# ) -# result = response['message']['content'] -# -# try: -# res = json.loads(result.split("<|python_tag|>")[-1]) -# function_name = res['name'] -# parameters = res['parameters'] -# return {"function_name": function_name, -# "parameters": parameters} -# except: -# return result -# -# def llama31(user_prompt: str, system_prompt = ""): response = ollama.chat(model='llama3.1', messages=[ diff --git a/docs/zero_to_hero_guide/gmail_agent/main.py b/docs/zero_to_hero_guide/gmail_agent/main.py index 468a42b58..537ad43c4 100644 --- a/docs/zero_to_hero_guide/gmail_agent/main.py +++ b/docs/zero_to_hero_guide/gmail_agent/main.py @@ -34,7 +34,7 @@ async def create_gmail_agent(client: LlamaStackClient) -> Agent: "temperature": 0.0, "top_p": 0.9, }, - tools=[ + tools = [ listEmailsTool.get_tool_definition(), getEmailDetailTool.get_tool_definition(), sendEmailTool.get_tool_definition(), @@ -43,27 +43,28 @@ async def create_gmail_agent(client: LlamaStackClient) -> Agent: sendDraftTool.get_tool_definition(), ], - tool_choice="auto", - tool_prompt_format="json", - input_shields=[], - output_shields=[], - enable_session_persistence=True + tool_choice = "auto", + tool_prompt_format = "json", + input_shields = [], + output_shields = [], + enable_session_persistence = True ) agent = Agent( - client=client, - agent_config=agent_config, - custom_tools=[listEmailsTool, - getEmailDetailTool, - sendEmailTool, - getPDFSummaryTool, - createDraftTool, - sendDraftTool] + client = client, + agent_config = agent_config, + custom_tools = ( + listEmailsTool, + getEmailDetailTool, + sendEmailTool, + getPDFSummaryTool, + createDraftTool, + sendDraftTool + ) ) return agent - async def main(): parser = argparse.ArgumentParser(description="Set email address") parser.add_argument("--gmail", type=str, required=True, help="Your Gmail address") @@ -74,8 +75,9 @@ async def main(): greeting = llama31("hello", "Your name is Gmagent, an assistant that can perform all Gmail related tasks for your user.") agent_response = f"{greeting}\n\nYour ask: " - # do i have emails with attachment larger than 5mb? - # what's the detail of the email with subject this is an interesting paper + client = LlamaStackClient(base_url=LLAMA_STACK_API_TOGETHER_URL) + agent = await create_gmail_agent(client) + session_id = agent.create_session("email-session") while True: ask = input(agent_response) @@ -84,10 +86,6 @@ async def main(): break print("\n-------------------------\nCalling Llama...") - client = LlamaStackClient(base_url=LLAMA_STACK_API_TOGETHER_URL) - agent = await create_gmail_agent(client) - session_id = agent.create_session("email-session") - response = agent.create_turn( messages=[{"role": "user", "content": ask}], session_id=session_id, @@ -97,8 +95,9 @@ async def main(): if log.role == "CustomTool": tool_name = json.loads(log.content)['name'] result = json.loads(log.content)['result'] + + # post processing if tool_name == 'list_emails': - # post processing memory['emails'] = result num = len(result) if num == 0: @@ -114,6 +113,15 @@ async def main(): elif tool_name == "get_email_detail": output = result + elif tool_name == "create_draft": + output = "Draft created." + memory['draft_id'] = result + elif tool_name == "send_draft": + output = result + elif tool_name == "send_email": + output = "Email sent." + elif tool_name == "get_pdf_summary": + output = result print(f"\n-------------------------\n\nGmagent: {output}\n") elif log.role == "inference": @@ -121,12 +129,7 @@ async def main(): else: print(log, end="") - - - agent_response = "\n\nYour ask: " - - - + agent_response = "Your ask: " if __name__ == "__main__": asyncio.run(main()) diff --git a/docs/zero_to_hero_guide/gmail_agent/requirements.txt b/docs/zero_to_hero_guide/gmail_agent/requirements.txt index b96e1f620..e1255e819 100644 --- a/docs/zero_to_hero_guide/gmail_agent/requirements.txt +++ b/docs/zero_to_hero_guide/gmail_agent/requirements.txt @@ -3,8 +3,9 @@ google-auth==2.27.0 google-auth-oauthlib==0.4.6 google-auth-httplib2==0.1.0 google-api-python-client==2.34.0 +llama_stack_client==0.0.50 pytz beautifulsoup4 -ollama +ollama==0.4.4 pypdf termcolor \ No newline at end of file