writinwaters commited on
Commit
d3d8d70
·
1 Parent(s): 3313a7c

0329 readme (#175)

Browse files

* Updated Get Started.

* Finishing off Get Started

* minor

* minor

Files changed (1) hide show
  1. README.md +28 -47
README.md CHANGED
@@ -45,22 +45,6 @@
45
  - The part of document cited in the answer is presented in the most expressive way.
46
  - For PDF file, the cited parts in document can be located in the original PDF.
47
 
48
- ## 🤺RagFlow vs. other RAG applications
49
-
50
- | Feature | RagFlow | Langchain-Chatchat | Assistants API | QAnythig | LangChain |
51
- |---------|:---------:|:-----------:|:-----------:|:-----------:|:-----------:|
52
- | **Well-Founded Answer** | :white_check_mark: | :x: | :x: | :x: | :x: |
53
- | **Trackable Chunking** | :white_check_mark: | :x: | :x: | :x: | :x: |
54
- | **Chunking Method** | Rich Variety | Naive | Naive | Naive | Naive |
55
- | **Table Structure Recognition** | :white_check_mark: | :x: | :x: | :x: | :x: |
56
- | **Structured Data Lookup** | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
57
- | **Programming Approach** | API-oriented | API-oriented | API-oriented | API-oriented | Python Code-oriented |
58
- | **RAG Engine** | :white_check_mark: | :white_check_mark: | :white_check_mark: | :x: | :x: |
59
- | **Prompt IDE** | :white_check_mark: | :white_check_mark: | :white_check_mark: | :x: | :x: |
60
- | **Supported LLMs** | Rich Variety | Rich Variety | OpenAI-only | QwenLLM | Rich Variety |
61
- | **Local Deployment** | :white_check_mark: | :white_check_mark: | :x: | :x: | :x: |
62
- | **Ecosystem Strategy** | Open Source | Open Source | Close Source | Open Source | Open Source |
63
-
64
  ## 🔎 System Architecture
65
 
66
  <div align="center" style="margin-top:20px;margin-bottom:20px;">
@@ -82,13 +66,14 @@
82
  > $ sysctl vm.max_map_count
83
  > ```
84
  >
85
- > Reset `vm.max_map_count` to a value greater than 65535 if it is not. In this case, we set it to 262144:
86
  >
87
  > ```bash
 
88
  > $ sudo sysctl -w vm.max_map_count=262144
89
  > ```
90
  >
91
- > This change will be reset after a system reboot. To ensure your change remains permanent, add or update the following line in **/etc/sysctl.conf** accordingly:
92
  >
93
  > ```bash
94
  > vm.max_map_count=262144
@@ -98,7 +83,7 @@
98
 
99
  ### Start up the RagFlow server
100
 
101
- 1. Clone the repo
102
 
103
  ```bash
104
  $ git clone https://github.com/infiniflow/ragflow.git
@@ -106,36 +91,33 @@
106
 
107
 
108
 
109
- 2.
110
 
111
- > - In [service_conf.yaml](./docker/service_conf.yaml), configuration of *LLM* in **user_default_llm** is strongly recommended.
112
- > In **user_default_llm** of [service_conf.yaml](./docker/service_conf.yaml), you need to specify LLM factory and your own _API_KEY_.
113
- > If you do not have _API_KEY_ at the moment, you can specify it in
114
- Settings the next time you log in to the system.
115
- > - RagFlow supports the flowing LLM factory, with more coming in the pipeline:
116
- > [OpenAI](https://platform.openai.com/login?launch), [Tongyi-Qianwen](https://dashscope.console.aliyun.com/model),
117
- > [ZHIPU-AI](https://open.bigmodel.cn/), [Moonshot](https://platform.moonshot.cn/docs/docs)
118
- ```bash
119
 
120
- $ cd ragflow/docker
121
- $ docker compose up -d
122
- ```
123
- ### OR
124
 
125
- ```bash
126
- $ git clone https://github.com/infiniflow/ragflow.git
127
- $ cd ragflow/
128
- $ docker build -t infiniflow/ragflow:v1.0 .
129
- $ cd ragflow/docker
130
- $ docker compose up -d
131
- ```
132
- > The core image is about 15 GB in size and may take a while to load.
 
 
 
 
133
 
134
- Check the server status after pulling all images and having Docker up and running:
135
- ```bash
136
- $ docker logs -f ragflow-server
137
- ```
138
- *The following output confirms the successful launch of the system:*
 
 
139
 
140
  ```bash
141
  ____ ______ __
@@ -149,10 +131,9 @@ $ docker logs -f ragflow-server
149
  * Running on http://127.0.0.1:9380
150
  * Running on http://172.22.0.5:9380
151
  INFO:werkzeug:Press CTRL+C to quit
152
-
153
  ```
154
- In your browser, enter the IP address of your server.
155
 
 
156
 
157
 
158
  ## 🔧 Configurations
 
45
  - The part of document cited in the answer is presented in the most expressive way.
46
  - For PDF file, the cited parts in document can be located in the original PDF.
47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  ## 🔎 System Architecture
49
 
50
  <div align="center" style="margin-top:20px;margin-bottom:20px;">
 
66
  > $ sysctl vm.max_map_count
67
  > ```
68
  >
69
+ > Reset `vm.max_map_count` to a value greater than 65535 if it is not.
70
  >
71
  > ```bash
72
+ > # In this case, we set it to 262144:
73
  > $ sudo sysctl -w vm.max_map_count=262144
74
  > ```
75
  >
76
+ > This change will be reset after a system reboot. To ensure your change remains permanent, add or update the `vm.max_map_count` value in **/etc/sysctl.conf** accordingly:
77
  >
78
  > ```bash
79
  > vm.max_map_count=262144
 
83
 
84
  ### Start up the RagFlow server
85
 
86
+ 1. Clone the repo:
87
 
88
  ```bash
89
  $ git clone https://github.com/infiniflow/ragflow.git
 
91
 
92
 
93
 
94
+ 2. **Recommended**: In **docker/service_conf.yaml**, select the desired LLM factory in `user_default_llm` and update the `API_KEY` field with your own.
95
 
96
+ > - You can still continue with the default settings, but it is highly recommended that you use your own API key the next time you log into the system.
97
+ > - RagFlow now supports the flowing LLM factories: OpenAI, Tongyi-Qianwen, ZHIPU-AI, and Moonshot.
 
 
 
 
 
 
98
 
99
+ 3. You now presented with two options for building the system: Using the pre-built images or building the images from source:
 
 
 
100
 
101
+ ```bash
102
+ # To use the pre-built images:
103
+ $ cd ragflow/docker
104
+ $ docker compose up -d
105
+ ```
106
+ ```bash
107
+ # To build the images from source:
108
+ $ cd ragflow/
109
+ $ docker build -t infiniflow/ragflow:v1.0 .
110
+ $ cd ragflow/docker
111
+ $ docker compose up -d
112
+ ```
113
 
114
+ > The core image is about 15 GB in size and may take a while to load.
115
+
116
+ 4. Check the server status after pulling all images and having Docker up and running:
117
+ ```bash
118
+ $ docker logs -f ragflow-server
119
+ ```
120
+ *The following output confirms a successful launch of the system:*
121
 
122
  ```bash
123
  ____ ______ __
 
131
  * Running on http://127.0.0.1:9380
132
  * Running on http://172.22.0.5:9380
133
  INFO:werkzeug:Press CTRL+C to quit
 
134
  ```
 
135
 
136
+ 5. In your browser, enter the IP address of your server and now you can try it out.
137
 
138
 
139
  ## 🔧 Configurations