ryefoxlime commited on
Commit
0ba2c42
1 Parent(s): f10c4c4

updates readme file

Browse files
Files changed (1) hide show
  1. README.md +50 -27
README.md CHANGED
@@ -9,72 +9,95 @@ app_file: app.py
9
  pinned: false
10
  short_description: Multi Agent crew for Market Analysis and Use Case Generation
11
  ---
 
12
  # Market Research & Use Case Generation Agent
 
13
  ## Project Overview
14
- ### Objective:
 
 
15
  Deploy Multi-Agent crew for Market Analysis and Use case Generator using Streamlit to provide an easy-to-use interface for model interaction.
16
- ### Technology:
 
 
17
  - Streamlit, an open-source Python library for building custom web applications for machine learning and data science.
18
  - CrewAI, an open-source library for building ai agents
19
 
20
- ### Model:
21
- #### LLMS
 
 
22
  - Uses gemini 1.5 flash version 002 as the base llm as it has the highest free token available to use while being fast and reliable when compared to other LLMs such as OpenAI, Anthropic etc
23
  - The model leverage the LiteLLM module as the backend for the LLM module in crewAI
24
 
25
  #### Crew
 
26
  The crew consists of 3 agents
27
- - Researcher:
28
- - Performs Market and Segment of the company
29
- - Identifies the Key offering in comparison to the competition in the same segment
30
- - Provides the strategic focus of the company
31
-
32
- > Tools: search_tool, web_search_tool, pdf_search_tool
33
- - Design Thinker
34
- - Analyzes the industry trends in the AI Space such as genai , llms etc using the information provided by the Researcher
35
- - Details some possible ideas using the mantra “Yes and …” while specifying the use cases, drawbacks and MVPs (Most Viable Product) to test the ideas
36
- - The agent empathises with shareholders, focusing on how these ideas may impact and benefit customers.
37
-
38
- > Tools: search_tool, web_search_tool, pdf_search_tool
39
-
40
- - Developer
41
- - Takes two projects(can be increased) and finds information such as datasets, research papers, similar projects etc
42
- - Gives suggestions on how this project can be modified for the company
43
-
44
- > Tools*: search_tool, web_search_tool, pdf_search_tool
45
-
 
 
 
46
  > NOTE: These results are a cause of publicly available information as it does not have information about the internal documents of the company
 
47
  ### Tools
48
- There are 3 primary tools used
 
 
49
  - [SerperDev](https://serper.dev/) to search the internet for relevant source materials
50
  - [WebsiteSearchTool](https://docs.crewai.com/tools/websitesearchtool) to perform RAG search within the content of a website
51
  - [PDF RAG](https://docs.crewai.com/tools/pdfsearchtool) Search to perform RAG search within PDF files sourced from the internet
52
 
53
  ## Implementation
 
54
  ### Streamlit Application Development
 
55
  **User Interface Design**: The Streamlit application was designed with a focus on user-friendliness and clarity. Key features include:
56
- - Input fields to input Serper API and Gemini API Keys
 
57
  - Input fields for user queries or data.
58
  - Output display area for model responses or generated results.
59
- - Ability to download outputs generated by each agent separately
60
 
61
  ### Intuitive navigation and controls.
 
62
  **CrewAI Integration**: The CrewAI model was seamlessly integrated into the Streamlit application.
63
 
64
  **Customization**: The application was customized to align with the specific requirements of the CrewAI model and its intended use cases.
65
 
66
  ## Deployment
 
67
  **Local Deployment**: The Streamlit application was initially deployed locally for testing and development purposes.
68
 
69
  **Cloud Deployment: (Optional)** The application was later deployed to a cloud platform Hugging Face for accessibility over the internet
70
 
71
  ## Conclusion
 
72
  This project successfully demonstrated the effective deployment of CrewAI using Streamlit. The resulting application provides a user-friendly and accessible interface for interacting with the model, making it easier for users to leverage its capabilities.
73
 
74
  ## Future Work
 
75
  **Enhanced Features**: Additional features could be added to the application, such as ability to choose LLM models, or integration of other tools.
76
 
77
  **Model Updates**: Providing an input field for users to customize the output or the task of each agent
78
 
79
  # High Level Design
80
- [![](https://mermaid.ink/img/pako:eNptkk2LwjAQhv_KEPCmgvXWw4JWhIVdWNbuqRUZm-kHtklJUkqx_vdNW5V23Tm9mWcy84bMlUWSE3NZnMs6SlEZ8HehABuzGfxoUvAuDKkYI4IPbEgNcBNgWS7L5giLxVt7IME1RLIoUTTzhzjVdNaZoRa2QaSo7sqH29v-1jeZSgkNpZIRaU0cOBpsYXMf0Rd5itCQhjVwWYtcIsdzThBnOekWdsFunN13WTvj-YCvoXUmkrH5fjx4qwATEkYvGyzy4wQ5gUF9eQX-KtCEKkpPRspcT5kT2AefRnyK10HJ4z_4adSTIs6SSqHJpIC9zPnDrK7OicIyvZdMWBfeaqSdQdvvGPX2O6v_93xFXfijlr4z0utRezZnBakCM26359qBkJmUCgqZayVHdQlZKG62DisjD42ImGtURXOmZJWkj0NV2l-nXYbWUcHcGHNts8QzI9XnsJv9it5-AbXs15o?type=png)](https://mermaid.live/edit#pako:eNptkk2LwjAQhv_KEPCmgvXWw4JWhIVdWNbuqRUZm-kHtklJUkqx_vdNW5V23Tm9mWcy84bMlUWSE3NZnMs6SlEZ8HehABuzGfxoUvAuDKkYI4IPbEgNcBNgWS7L5giLxVt7IME1RLIoUTTzhzjVdNaZoRa2QaSo7sqH29v-1jeZSgkNpZIRaU0cOBpsYXMf0Rd5itCQhjVwWYtcIsdzThBnOekWdsFunN13WTvj-YCvoXUmkrH5fjx4qwATEkYvGyzy4wQ5gUF9eQX-KtCEKkpPRspcT5kT2AefRnyK10HJ4z_4adSTIs6SSqHJpIC9zPnDrK7OicIyvZdMWBfeaqSdQdvvGPX2O6v_93xFXfijlr4z0utRezZnBakCM26359qBkJmUCgqZayVHdQlZKG62DisjD42ImGtURXOmZJWkj0NV2l-nXYbWUcHcGHNts8QzI9XnsJv9it5-AbXs15o)
 
 
9
  pinned: false
10
  short_description: Multi Agent crew for Market Analysis and Use Case Generation
11
  ---
12
+
13
  # Market Research & Use Case Generation Agent
14
+
15
  ## Project Overview
16
+
17
+ ### Objective:
18
+
19
  Deploy Multi-Agent crew for Market Analysis and Use case Generator using Streamlit to provide an easy-to-use interface for model interaction.
20
+
21
+ ### Technology:
22
+
23
  - Streamlit, an open-source Python library for building custom web applications for machine learning and data science.
24
  - CrewAI, an open-source library for building ai agents
25
 
26
+ ### Model:
27
+
28
+ #### LLMS
29
+
30
  - Uses gemini 1.5 flash version 002 as the base llm as it has the highest free token available to use while being fast and reliable when compared to other LLMs such as OpenAI, Anthropic etc
31
  - The model leverage the LiteLLM module as the backend for the LLM module in crewAI
32
 
33
  #### Crew
34
+
35
  The crew consists of 3 agents
36
+
37
+ - Researcher:
38
+
39
+ - Performs Market and Segment of the company
40
+ - Identifies the Key offering in comparison to the competition in the same segment
41
+ - Provides the strategic focus of the company
42
+
43
+ > Tools: search_tool, web_search_tool, pdf_search_tool
44
+
45
+ - Design Thinker
46
+
47
+ - Analyzes the industry trends in the AI Space such as genai , llms etc using the information provided by the Researcher
48
+ - Details some possible ideas using the mantra “Yes and …” while specifying the use cases, drawbacks and MVPs (Most Viable Product) to test the ideas
49
+ - The agent empathises with shareholders, focusing on how these ideas may impact and benefit customers.
50
+
51
+ > Tools: search_tool, web_search_tool, pdf_search_tool
52
+
53
+ - Developer
54
+ - Takes two projects(can be increased) and finds information such as datasets, research papers, similar projects etc
55
+ - Gives suggestions on how this project can be modified for the company
56
+ > Tools\*: search_tool, web_search_tool, pdf_search_tool
57
+
58
  > NOTE: These results are a cause of publicly available information as it does not have information about the internal documents of the company
59
+
60
  ### Tools
61
+
62
+ There are 3 primary tools used
63
+
64
  - [SerperDev](https://serper.dev/) to search the internet for relevant source materials
65
  - [WebsiteSearchTool](https://docs.crewai.com/tools/websitesearchtool) to perform RAG search within the content of a website
66
  - [PDF RAG](https://docs.crewai.com/tools/pdfsearchtool) Search to perform RAG search within PDF files sourced from the internet
67
 
68
  ## Implementation
69
+
70
  ### Streamlit Application Development
71
+
72
  **User Interface Design**: The Streamlit application was designed with a focus on user-friendliness and clarity. Key features include:
73
+
74
+ - Input fields to input Serper API and Gemini API Keys
75
  - Input fields for user queries or data.
76
  - Output display area for model responses or generated results.
77
+ - Ability to download outputs generated by each agent separately
78
 
79
  ### Intuitive navigation and controls.
80
+
81
  **CrewAI Integration**: The CrewAI model was seamlessly integrated into the Streamlit application.
82
 
83
  **Customization**: The application was customized to align with the specific requirements of the CrewAI model and its intended use cases.
84
 
85
  ## Deployment
86
+
87
  **Local Deployment**: The Streamlit application was initially deployed locally for testing and development purposes.
88
 
89
  **Cloud Deployment: (Optional)** The application was later deployed to a cloud platform Hugging Face for accessibility over the internet
90
 
91
  ## Conclusion
92
+
93
  This project successfully demonstrated the effective deployment of CrewAI using Streamlit. The resulting application provides a user-friendly and accessible interface for interacting with the model, making it easier for users to leverage its capabilities.
94
 
95
  ## Future Work
96
+
97
  **Enhanced Features**: Additional features could be added to the application, such as ability to choose LLM models, or integration of other tools.
98
 
99
  **Model Updates**: Providing an input field for users to customize the output or the task of each agent
100
 
101
  # High Level Design
102
+
103
+ [![](https://mermaid.ink/img/pako:eNptkk2LwjAQhv_KEPCmgvXWw4JWhIVdWNbuqRUZm-kHtklJUkqx_vdNW5V23Tm9mWcy84bMlUWSE3NZnMs6SlEZ8HehABuzGfxoUvAuDKkYI4IPbEgNcBNgWS7L5giLxVt7IME1RLIoUTTzhzjVdNaZoRa2QaSo7sqH29v-1jeZSgkNpZIRaU0cOBpsYXMf0Rd5itCQhjVwWYtcIsdzThBnOekWdsFunN13WTvj-YCvoXUmkrH5fjx4qwATEkYvGyzy4wQ5gUF9eQX-KtCEKkpPRspcT5kT2AefRnyK10HJ4z_4adSTIs6SSqHJpIC9zPnDrK7OicIyvZdMWBfeaqSdQdvvGPX2O6v_93xFXfijlr4z0utRezZnBakCM26359qBkJmUCgqZayVHdQlZKG62DisjD42ImGtURXOmZJWkj0NV2l-nXYbWUcHcGHNts8QzI9XnsJv9it5-AbXs15o?type=png)](https://mermaid.live/edit#pako:eNptkk2LwjAQhv_KEPCmgvXWw4JWhIVdWNbuqRUZm-kHtklJUkqx_vdNW5V23Tm9mWcy84bMlUWSE3NZnMs6SlEZ8HehABuzGfxoUvAuDKkYI4IPbEgNcBNgWS7L5giLxVt7IME1RLIoUTTzhzjVdNaZoRa2QaSo7sqH29v-1jeZSgkNpZIRaU0cOBpsYXMf0Rd5itCQhjVwWYtcIsdzThBnOekWdsFunN13WTvj-YCvoXUmkrH5fjx4qwATEkYvGyzy4wQ5gUF9eQX-KtCEKkpPRspcT5kT2AefRnyK10HJ4z_4adSTIs6SSqHJpIC9zPnDrK7OicIyvZdMWBfeaqSdQdvvGPX2O6v_93xFXfijlr4z0utRezZnBakCM26359qBkJmUCgqZayVHdQlZKG62DisjD42ImGtURXOmZJWkj0NV2l-nXYbWUcHcGHNts8QzI9XnsJv9it5-AbXs15o)