diff --git a/recipes/use_cases/email_agent/1.png b/recipes/use_cases/email_agent/1.png
index 639c905c2cd4ffcf7fe866b43615e3d33001b03a..2793199db6173abc5446ea02024bf6fb70736ef6 100644
Binary files a/recipes/use_cases/email_agent/1.png and b/recipes/use_cases/email_agent/1.png differ
diff --git a/recipes/use_cases/email_agent/2.png b/recipes/use_cases/email_agent/2.png
index e80f894f1c30d15c67f134e2c156269b74825160..5b618ec0f8799ecdb173541e1de7d802f263948e 100644
Binary files a/recipes/use_cases/email_agent/2.png and b/recipes/use_cases/email_agent/2.png differ
diff --git a/recipes/use_cases/email_agent/3.png b/recipes/use_cases/email_agent/3.png
index d74b7d49d437290afeed4c6670e18635e6624384..fba755085564b4f9ecfc652de79a704eba849e54 100644
Binary files a/recipes/use_cases/email_agent/3.png and b/recipes/use_cases/email_agent/3.png differ
diff --git a/recipes/use_cases/email_agent/README.md b/recipes/use_cases/email_agent/README.md
index e5ce904710aec651422de79e5d0e7cf4877527f8..ae9961707b0a67a7c21cd7342d5311edee1e37b9 100644
--- a/recipes/use_cases/email_agent/README.md
+++ b/recipes/use_cases/email_agent/README.md
@@ -52,9 +52,9 @@ Yet another simple [summary](https://www.felicis.com/insight/the-agentic-web) by
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 Emagent:
+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 the agent:
-# Example Asks to Emagent
+# Example Asks to Email Agent
* do i have any emails with attachments?
* what's the content of the email from LangSmith
@@ -70,7 +70,10 @@ It's time to see an agent app in action and enjoy some coding. Below is a previe
* how many emails do i have from xxx@gmail.com?
* how about from yyy@gmail.com?
-[Here](./examples_log.txt) is an example interaction log with Emagent.
+Below are screenshots of some example interactions with the agent:
+
+
+
# Setup and Installation
@@ -99,14 +102,14 @@ This will download a quantized version of Llama 3.1 of the size 4.7GB.
First, create a Conda or virtual env:
```
-conda create -n emagent python=3.10
-conda activate emagent
+conda create -n emailagent python=3.10
+conda activate emailagent
```
or
```
-python -m venv emagent
-source emagent/bin/activate # on Linux, macOS:
-source emagent\Scripts\activate # on Windows
+python -m venv emailagent
+source emailagent/bin/activate # on Linux, macOS:
+source emailagent\Scripts\activate # on Windows
```
Then install the required Python libraries:
@@ -116,9 +119,9 @@ cd llama-recipes/recipes/use_cases/email_agent
pip install -r requirements.txt
```
-# Run Emagent
+# Run Email Agent
-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 emagent folder, then run:
+To run the agent, 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 <your_gmail_address>
```
diff --git a/recipes/use_cases/email_agent/examples_log.txt b/recipes/use_cases/email_agent/examples_log.txt
deleted file mode 100644
index 15d01e7dc68b0ed2e453f68e742577cc1441304f..0000000000000000000000000000000000000000
--- a/recipes/use_cases/email_agent/examples_log.txt
+++ /dev/null
@@ -1,230 +0,0 @@
-python main.py --gmail=gmagent_tester1@gmail.com
-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 gmagent_tester2@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': 'gmagent_tester2@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': 'gmagent_tester2@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 gmagent_tester2@meta.com
-
--------------------------
-Calling Llama...
-
-Llama returned: {'function_name': 'send_email', 'parameters': {'action': 'forward', 'to': 'gmagent_tester2@meta.com', 'subject': 'this is an interesting paper', 'body': '', 'email_id': '1936fce85e88a3ef'}}.
-
-Calling tool to access Gmail API: send_email, {'action': 'forward', 'to': 'gmagent_tester2@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: