gmagent v.1

recipes/use_cases/gmail_agent/LICENSE

+MIT License
+
+Copyright (c) 2024 Jeff Tang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

recipes/use_cases/gmail_agent/examples_log.txt

+python  main.py
+Hello! I'm Gmagent, your friendly Gmail assistant. I'm here to help you with any Gmail-related tasks. What can I do for you today? Do you need help checking email, composing a new message, or perhaps something else?
+
+Your ask: do i have any emails with attachments?
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'list_emails', 'parameters': {'query': 'has:attachment'}}.
+
+Calling tool to access Gmail API: list_emails, {'query': '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 <gmagent_tester2@gmail.com>', 'subject': 'papers to read', 'received_time': '2024-11-26 18:44:19 PST'}, {'message_id': '18fa7f38f83197d3', 'sender': 'LangSmith <noreply@langchain.com>', 'subject': 'New Data Retention policy for LangSmith', 'received_time': '2024-05-23 17:14:22 PDT'}]
+
+-------------------------
+
+Gmagent: I found 3 emails matching your query:
+1. From: gmagent_tester1@gmail.com, Subject: Fwd: papers to read, Received on: 2024-11-27 10:51:51 PST
+2. From: Jeff Tang <gmagent_tester2@gmail.com>, Subject: papers to read, Received on: 2024-11-26 18:44:19 PST
+3. From: LangSmith <noreply@langchain.com>, Subject: New Data Retention policy for LangSmith, Received on: 2024-05-23 17:14:22 PDT
+
+
+Your ask: what's the content of the email from LangSmith
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'get_email_detail', 'parameters': {'detail': 'body', 'which': 'from <sender info>'}}.
+
+Calling tool to access Gmail API: get_email_detail, {'detail': 'body', 'which': '18fa7f38f83197d3'}...
+
+Tool calling returned: New Data Retention policy for LangSmith
+Hi Jeff,
+You are receiving this email because you have an active account on LangSmith. We are transitioning to a new data retention strategy that limits the length of time trace data is stored in LangSmith.
+Effective with traces received on or after Wednesday, May 22, all traces stored in LangSmith now have a maximum retention of 400 days from the time of ingest.
+For more information about this change please visit the LangSmith Docs.
+If after visiting the docs you still have additional questions, please reach out to LangSmith Support via support@langchain.dev or, if you are an Enterprise plan customer, your dedicated Slack channel.
+
+-------------------------
+
+Gmagent: New Data Retention policy for LangSmith
+Hi Jeff,
+You are receiving this email because you have an active account on LangSmith. We are transitioning to a new data retention strategy that limits the length of time trace data is stored in LangSmith.
+Effective with traces received on or after Wednesday, May 22, all traces stored in LangSmith now have a maximum retention of 400 days from the time of ingest.
+For more information about this change please visit the LangSmith Docs.
+If after visiting the docs you still have additional questions, please reach out to LangSmith Support via support@langchain.dev or, if you are an Enterprise plan customer, your dedicated Slack channel.
+
+
+
+
+
+
+
+
+Unsubscribe
+
+Your ask: do i have emails with attachment larger than 1mb?
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'list_emails', 'parameters': {'query': 'has:attachment larger:1mb'}}.
+
+Calling tool to access Gmail API: list_emails, {'query': 'has:attachment larger:1mb'}...
+
+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 <gmagent_tester2@gmail.com>', 'subject': 'papers to read', 'received_time': '2024-11-26 18:44:19 PST'}]
+
+-------------------------
+
+Gmagent: I found 2 emails matching your query:
+1. From: gmagent_tester1@gmail.com, Subject: Fwd: papers to read, Received on: 2024-11-27 10:51:51 PST
+2. From: Jeff Tang <gmagent_tester2@gmail.com>, Subject: papers to read, Received on: 2024-11-26 18:44:19 PST
+
+
+Your ask: what kind of attachments for the email with subject papers to read?
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'get_email_detail', 'parameters': {'detail': 'attachment', 'which': 'subject papers to read'}}.
+
+Calling tool to access Gmail API: get_email_detail, {'detail': 'attachment', 'which': '1936b819706a4923'}...
+
+Tool calling returned: thinking_llm.pdf - 1115430 bytes
+logic-of-thought.pdf - 1719126 bytes
+
+
+-------------------------
+
+Gmagent: thinking_llm.pdf - 1115430 bytes
+logic-of-thought.pdf - 1719126 bytes
+
+
+Your ask: give me a summary of the pdf thinking_llm.pdf
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'get_pdf_summary', 'parameters': {'file_name': 'thinking_llm.pdf'}}.
+
+Calling tool to access Gmail API: get_pdf_summary, {'file_name': 'thinking_llm.pdf'}...
+
+PDF text length: 80464
+
+Calling Llama 31 to generate a summary...
+
+Tool calling returned: It appears that you've provided several examples of responses generated by a model, along with some analysis and comparisons.
+
+From what I can see, these examples illustrate various aspects of model performance, including:
+
+1. **Inconsistent or incorrect outputs**: In some cases, the model generates responses that are not accurate or consistent (e.g., Examples 17-19).
+2. **Self-correction in math tasks**: The model sometimes makes mistakes but then corrects them based on further thought and analysis (e.g., Example 20).
+3. **Improved performance with specific prompts**: Using specific prompts can help the model generate more accurate or helpful responses, especially in cases where it initially made a mistake (e.g., Examples 17-19).
+4. **Comparison to direct models**: The TPO model's ability to correct its own mistakes and generate more accurate responses is highlighted through comparisons with direct models (e.g., Example 20).
+
+These examples are likely from the report you mentioned, which explores the performance of a sequence-to-sequence model for generating natural language responses.
+
+If you'd like to discuss any specific points or ask questions about these examples, I'm here to help!
+
+-------------------------
+
+Gmagent: It appears that you've provided several examples of responses generated by a model, along with some analysis and comparisons.
+
+From what I can see, these examples illustrate various aspects of model performance, including:
+
+1. **Inconsistent or incorrect outputs**: In some cases, the model generates responses that are not accurate or consistent (e.g., Examples 17-19).
+2. **Self-correction in math tasks**: The model sometimes makes mistakes but then corrects them based on further thought and analysis (e.g., Example 20).
+3. **Improved performance with specific prompts**: Using specific prompts can help the model generate more accurate or helpful responses, especially in cases where it initially made a mistake (e.g., Examples 17-19).
+4. **Comparison to direct models**: The TPO model's ability to correct its own mistakes and generate more accurate responses is highlighted through comparisons with direct models (e.g., Example 20).
+
+These examples are likely from the report you mentioned, which explores the performance of a sequence-to-sequence model for generating natural language responses.
+
+If you'd like to discuss any specific points or ask questions about these examples, I'm here to help!
+
+Your ask: Draft an email to jeffxtang@meta.com saying working on it and will keep you updated. thanks for your patience.
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'create_draft', 'parameters': {'action': 'new', 'to': 'jeffxtang@meta.com', 'subject': 'Update on [Your Project]', 'body': 'Hi Jeff,\\n\\nI wanted to touch base with you regarding [Your Project]. I am currently working on it and will keep you updated. Thank you for your patience.\\n\\nBest regards,'}}.
+
+Calling tool to access Gmail API: create_draft, {'action': 'new', 'to': 'jeffxtang@meta.com', 'subject': 'Update on [Your Project]', 'body': 'Hi Jeff,\\n\\nI wanted to touch base with you regarding [Your Project]. I am currently working on it and will keep you updated. Thank you for your patience.\\n\\nBest regards,'}...
+Draft created with ID: r5930232887125763038
+
+Tool calling returned: r5930232887125763038
+
+-------------------------
+
+Gmagent: Draft created.
+
+Your ask: send the draft
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'send_draft', 'parameters': {'id': '...'}}.
+
+Calling tool to access Gmail API: send_draft, {'id': 'r5930232887125763038'}...
+
+Tool calling returned: Draft sent with email ID: 1936fc3db1993629
+
+-------------------------
+
+Gmagent: Draft sent with email ID: 1936fc3db1993629
+
+Your ask: do i have any emails with attachment larger than 10mb?
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'list_emails', 'parameters': {'query': 'has:attachment larger:10mb'}}.
+
+Calling tool to access Gmail API: list_emails, {'query': 'has:attachment larger:10mb'}...
+
+Tool calling returned: []
+
+-------------------------
+
+Gmagent: I couldn't find any such emails. What else would you like to do?
+
+Your ask: how about 5mb
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'list_emails', 'parameters': {'query': 'has:attachment larger:5mb'}}.
+
+Calling tool to access Gmail API: list_emails, {'query': 'has:attachment larger:5mb'}...
+
+Tool calling returned: [{'message_id': '1936fce85e88a3ef', 'sender': 'Jeff Tang <gmagent_tester2@gmail.com>', 'subject': 'this is an interesting paper', 'received_time': '2024-11-27 14:46:50 PST'}]
+
+-------------------------
+
+Gmagent: I found 1 email matching your query:
+1. From: Jeff Tang <gmagent_tester2@gmail.com>, Subject: this is an interesting paper, Received on: 2024-11-27 14:46:50 PST
+
+
+Your ask: reply to the email saying thanks for sharing!
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'send_email', 'parameters': {'action': 'reply', 'to': 'gmagent_tester2@gmail.com', 'subject': 'Re: this is an interesting paper', 'body': 'Thanks for sharing!', 'email_id': '1936fce85e88a3ef'}}.
+
+Calling tool to access Gmail API: send_email, {'action': 'reply', 'to': 'gmagent_tester2@gmail.com', 'subject': 'Re: this is an interesting paper', 'body': 'Thanks for sharing!', 'email_id': '1936fce85e88a3ef'}...
+Reply sent. Message ID: 1936fd65f9f24e70
+
+Tool calling returned: None
+
+-------------------------
+
+Gmagent: Email sent.
+
+Your ask: forward the email to jeffxtang@meta.com
+
+-------------------------
+Calling Llama...
+
+Llama returned: {'function_name': 'send_email', 'parameters': {'action': 'forward', 'to': 'jeffxtang@meta.com', 'subject': 'this is an interesting paper', 'body': '', 'email_id': '1936fce85e88a3ef'}}.
+
+Calling tool to access Gmail API: send_email, {'action': 'forward', 'to': 'jeffxtang@meta.com', 'subject': 'this is an interesting paper', 'body': '', 'email_id': '1936fce85e88a3ef'}...
+Message forwarded successfully! Message ID: 1936fdd039c68451
+
+Tool calling returned: None
+
+-------------------------
+
+Gmagent: Email sent.
+
+Your ask:

recipes/use_cases/gmail_agent/functions_prompt.py

+list_emails_function = """
+{
+    "type": "function",
+    "function": {
+        "name": "list_emails",
+        "description": "Return a list of emails matching an optionally specified query.",
+        "parameters": {
+            "type": "dic",
+            "properties": [
+                {
+                    "maxResults": {
+                        "type": "integer",
+                        "description": "The default maximum number of emails to return is 100; the maximum allowed value for this field is 500."
+                    }
+                },              
+                {
+                    "query": {
+                        "type": "string",
+                        "description": "One or more keywords in the email subject and body, or one or more filters. There can be 6 types of filters: 1) Field-specific Filters: from, to, cc, bcc, subject; 2) Date Filters: before, after, older than, newer than); 3) Status Filters: read, unread, starred, importatant; 4) Attachment Filters: has, filename or type; 5) Size Filters: larger, smaller; 6) logical operators (or, and, not)."
+                    }
+                }
+            ],
+            "required": []
+        }
+    }
+}
+"""
+
+get_email_function = """
+{
+    "type": "function",
+    "function": {
+        "name": "get_email_detail",
+        "description": "Get detailed info about a specific email",
+        "parameters": {
+            "type": "dict",
+            "properties": [
+                {
+                    "detail": {
+                        "type": "string",
+                        "description": "what detail the user wants to know about - two possible values: body or attachment"
+                    }
+                },
+                {
+                    "which": {
+                        "type": "string",
+                        "description": "which email to get detail about - possible values include: 'first', 'second', ..., 'last', 'from ...', and 'subject ...'"
+                    }
+                },
+            ],
+            "required": ["detail", "which"]
+        }
+    }
+}
+"""
+
+send_email_function = """
+{
+    "type": "function",
+    "function": {
+        "name": "send_email",
+        "description": "Compose, reply, or forward email",
+        "parameters": {
+            "type": "dict",
+            "properties": [
+                {
+                    "action": {
+                        "type": "string",
+                        "description": "Whether to compose, reply, or forward an email"
+                    }
+                },
+                {
+                    "to": {
+                        "type": "string",
+                        "description": "The recipient of the email"
+                    }
+                },
+                {
+                    "subject": {
+                        "type": "string",
+                        "description": "The email subject"
+                    }
+                },
+                {
+                    "body": {
+                        "type": "string",
+                        "description": "The email content"
+                    }
+                },                                
+                {
+                    "email_id": {
+                        "type": "string",
+                        "description": "the email id to reply or forward to"
+                    }
+                }
+            ],
+            "required": ["action", "to", "subject", "body"]
+        }
+    }
+}
+"""
+
+get_pdf_summary_function = """
+{
+    "type": "function",
+    "function": {
+        "name": "get_pdf_summary",
+        "description": "get a summary of a PDF attachment",
+        "parameters": {
+            "type": "dict",
+            "properties": [
+                {
+                    "file_name": {
+                        "type": "string",
+                        "description": "The name of the PDF file"
+                    }
+                },
+            ],
+            "required": ["file_name"]
+        }
+    }
+}
+"""
+
+create_draft_function = """
+{
+    "type": "function",
+    "function": {
+        "name": "create_draft",
+        "description": "Create a new, reply, or forward email draft",
+        "parameters": {
+            "type": "dict",
+            "properties": [
+                {
+                    "action": {
+                        "type": "string",
+                        "description": "Whether to draft a new, reply, or forward an email"
+                    }
+                },
+                {
+                    "to": {
+                        "type": "string",
+                        "description": "The recipient of the email"
+                    }
+                },
+                {
+                    "subject": {
+                        "type": "string",
+                        "description": "The email subject"
+                    }
+                },
+                {
+                    "body": {
+                        "type": "string",
+                        "description": "The email content"
+                    }
+                },                                
+                {
+                    "email_id": {
+                        "type": "string",
+                        "description": "the email id to reply or forward to, or empty if draft a new email."
+                    }
+                }
+            ],
+            "required": ["action", "to", "subject", "body", "email_id"]
+        }
+    }
+}
+"""
+
+# for now, only allow for one draft email to be saved in a session
+# to support for multiple drafts, cf how get_email_detail after list_emails is implemented.
+send_draft_function = """
+{
+    "type": "function",
+    "function": {
+        "name": "send_draft",
+        "description": "Send a draft email",
+        "parameters": {
+            "type": "dict",
+            "properties": [
+                {
+                    "id": {
+                        "type": "string",
+                        "description": "draft id"
+                    }
+                },        
+            ],
+            "required": ["id"]        
+        }
+    }
+}
+"""
+
+examples = """
+{"name": "list_emails", "parameters": {"query": "has:attachment larger:5mb"}}
+{"name": "list_emails", "parameters": {"query": "has:attachment"}}
+{"name": "list_emails", "parameters": {"query": "newer_than:1d"}}
+{"name": "list_emails", "parameters": {"query": "older_than:1d"}}
+{"name": "list_emails", "parameters": {"query": "is:unread"}}
+{"name": "list_emails", "parameters":  {"query": "<query> is:unread"}}
+{"name": "list_emails", "parameters":  {"query": "<query> is:read"}}
+{"name": "get_email_detail", "parameters": {"detail": "body", "which": "first"}}
+{"name": "get_email_detail", "parameters": {"detail": "body", "which": "last"}}
+{"name": "get_email_detail", "parameters": {"detail": "body", "which": "second"}}
+{"name": "get_email_detail", "parameters": {"detail": "body", "which": "subject <subject info>"}}
+{"name": "get_email_detail", "parameters": {"detail": "attachment", "which": "from <sender info>"}}
+{"name": "get_email_detail", "parameters": {"detail": "attachment", "which": "first"}}
+{"name": "get_email_detail", "parameters": {"detail": "attachment", "which": "last"}}
+{"name": "get_email_detail", "parameters": {"detail": "attachment", "which": "<email id>"}}
+{"name": "send_email", "parameters": {"action": "compose", "to": "jeffxtang@meta.com", "subject": "xxxxx", "body": "xxxxx"}}
+{"name": "send_email", "parameters": {"action": "reply", "to": "", "subject": "xxxxx", "body": "xxxxx", "email_id": "xxxxx"}}
+{"name": "send_email", "parameters": {"action": "forward", "to": "jeffxtang@meta.com", "subject": "xxxxx", "body": "xxxxx", "email_id": "xxxxx"}}
+{"name": "create_draft", "parameters": {"action": "new", "to": "jeffxtang@meta.com", "subject": "xxxxx", "body": "xxxxx", "email_id": ""}}
+{"name": "create_draft", "parameters": {"action": "reply", "to": "", "subject": "xxxxx", "body": "xxxxx", "email_id": "xxxxx"}}
+{"name": "create_draft", "parameters": {"action": "forward", "to": "jeffxtang@meta.com", "subject": "xxxxx", "body": "xxxxx", "email_id": "xxxxx"}}
+{"name": "send_draft", "parameters": {"id": "..."}}
+{"name": "get_pdf_summary", "parameters": {"file_name": "..."}}
+"""
+
+system_prompt = f"""
+Environment: ipython
+Cutting Knowledge Date: December 2023
+Today Date: 1 December 2024
+
+Your name is Gmagent, an assistant that can perform all Gmail related tasks for your user.
+Respond to the user's ask by making use of the following functions if needed.
+If no available functions can be used, just say "I don't know" and don't make up facts.
+Here is a list of available functions in JSON format:
+
+{list_emails_function}
+{get_email_function}
+{send_email_function}
+{get_pdf_summary_function}
+{create_draft_function}
+{send_draft_function}
+
+Example responses:
+{examples}
+
+"""

recipes/use_cases/gmail_agent/main.py

+import argparse
+import gmagent
+from gmagent import *
+from functions_prompt import system_prompt
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Set email address")
+    parser.add_argument("--user_email", type=str, required=True, help="Your Gmail address")
+    args = parser.parse_args()
+
+    gmagent.set_email_service(args.user_email)
+
+    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: "
+    agent = Agent(system_prompt)
+
+    while True:
+        ask = input(agent_response)
+        if ask == "bye":
+            print(llama31("bye"))
+            break
+        print("\n-------------------------\nCalling Llama...")
+        agent(ask)
+        agent_response = "Your ask: "
+
+
+if __name__ == "__main__":
+    main()
+
+
+

recipes/use_cases/gmail_agent/requirements.txt

+
+google-auth==2.27.0
+google-auth-oauthlib==0.4.6
+google-auth-httplib2==0.1.0
+google-api-python-client==2.34.0
+pytz
+beautifulsoup4
+ollama
+pypdf
\ No newline at end of file