writinwaters commited on
Commit
47731cb
·
1 Parent(s): 21e42fc

Miscellaneous updates (#4228)

Browse files

### What problem does this PR solve?


### Type of change


- [x] Documentation Update

docs/guides/agentic_rag/agent_component_reference/_category_.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label": "Agent Component Reference",
3
+ "position": 1,
4
+ "link": {
5
+ "type": "generated-index",
6
+ "description": "A complete reference for RAGFlow's agent components."
7
+ }
8
+ }
docs/guides/agentic_rag/agent_introduction.md CHANGED
@@ -5,6 +5,12 @@ slug: /agent_introduction
5
 
6
  # Introduction to agents
7
 
 
 
 
 
 
 
8
  Agents and RAG are complementary techniques, each enhancing the other’s capabilities in business applications. RAGFlow v0.8.0 introduces an agent mechanism, featuring a no-code workflow editor on the front end and a comprehensive graph-based task orchestration framework on the back end. This mechanism is built on top of RAGFlow's existing RAG solutions and aims to orchestrate search technologies such as query intent classification, conversation leading, and query rewriting to:
9
 
10
  - Provide higher retrievals and,
@@ -23,7 +29,7 @@ Before proceeding, ensure that:
23
 
24
  Click the **Agent** tab in the middle top of the page to show the **Agent** page. As shown in the screenshot below, the cards on this page represent the created agents, which you can continue to edit.
25
 
26
- ![agents](https://github.com/user-attachments/assets/5e10758b-ec43-49ae-bf91-ff7d04c56e9d)
27
 
28
  We also provide templates catered to different business scenarios. You can either generate your agent from one of our agent templates or create one from scratch:
29
 
@@ -35,7 +41,7 @@ We also provide templates catered to different business scenarios. You can eithe
35
 
36
  *You are now taken to the **no-code workflow editor** page. The left panel lists the components (operators): Above the dividing line are the RAG-specific components; below the line are tools. We are still working to expand the component list.*
37
 
38
- ![workflow_editor](https://github.com/user-attachments/assets/9fc6891c-7784-43b8-ab4a-3b08a9e551c4)
39
 
40
  4. General speaking, now you can do the following:
41
  - Drag and drop a desired component to your workflow,
@@ -58,7 +64,7 @@ Please review the flowing description of the RAG-specific components before you
58
  | **Message** | A component that sends out a static message. If multiple messages are supplied, it randomly selects one to send. Ensure its downstream is **Interact**, the interface component. |
59
  | **Relevant** | A component that uses the LLM to assess whether the upstream output is relevant to the user's latest query. Ensure you specify the next component for each judge result. |
60
  | **Rewrite** | A component that refines a user query if it fails to retrieve relevant information from the knowledge base. It repeats this process until the predefined looping upper limit is reached. Ensure its upstream is **Relevant** and downstream is **Retrieval**. |
61
- | **Keyword** | A component that retrieves top N search results from wikipedia.org. Ensure the TopN value is set properly before use. |
62
 
63
  :::caution NOTE
64
 
 
5
 
6
  # Introduction to agents
7
 
8
+ Key concepts, basic operations, a quick view of the agent editor.
9
+
10
+ ---
11
+
12
+ ## Key concepts
13
+
14
  Agents and RAG are complementary techniques, each enhancing the other’s capabilities in business applications. RAGFlow v0.8.0 introduces an agent mechanism, featuring a no-code workflow editor on the front end and a comprehensive graph-based task orchestration framework on the back end. This mechanism is built on top of RAGFlow's existing RAG solutions and aims to orchestrate search technologies such as query intent classification, conversation leading, and query rewriting to:
15
 
16
  - Provide higher retrievals and,
 
29
 
30
  Click the **Agent** tab in the middle top of the page to show the **Agent** page. As shown in the screenshot below, the cards on this page represent the created agents, which you can continue to edit.
31
 
32
+ ![agent_mainpage](https://github.com/user-attachments/assets/5c0bb123-8f4e-42ea-b250-43f640dc6814)
33
 
34
  We also provide templates catered to different business scenarios. You can either generate your agent from one of our agent templates or create one from scratch:
35
 
 
41
 
42
  *You are now taken to the **no-code workflow editor** page. The left panel lists the components (operators): Above the dividing line are the RAG-specific components; below the line are tools. We are still working to expand the component list.*
43
 
44
+ ![workflow_editor](https://github.com/user-attachments/assets/47b4d5ce-b35a-4d6b-b483-ba495a75a65d)
45
 
46
  4. General speaking, now you can do the following:
47
  - Drag and drop a desired component to your workflow,
 
64
  | **Message** | A component that sends out a static message. If multiple messages are supplied, it randomly selects one to send. Ensure its downstream is **Interact**, the interface component. |
65
  | **Relevant** | A component that uses the LLM to assess whether the upstream output is relevant to the user's latest query. Ensure you specify the next component for each judge result. |
66
  | **Rewrite** | A component that refines a user query if it fails to retrieve relevant information from the knowledge base. It repeats this process until the predefined looping upper limit is reached. Ensure its upstream is **Relevant** and downstream is **Retrieval**. |
67
+ | **Keyword** | A component that extracts keywords from a user query, with TopN specifying the number of keywords to extract. |
68
 
69
  :::caution NOTE
70
 
docs/references/http_api_reference.md CHANGED
@@ -883,6 +883,10 @@ Failure:
883
 
884
  ---
885
 
 
 
 
 
886
  ### Add chunk
887
 
888
  **POST** `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks`
@@ -936,9 +940,7 @@ Success:
936
  "content": "ragflow content",
937
  "create_time": "2024-10-16 08:05:04",
938
  "create_timestamp": 1729065904.581025,
939
- "dataset_id": [
940
- "c7ee74067a2c11efb21c0242ac120006"
941
- ],
942
  "document_id": "5c5999ec7be811ef9cab0242ac120005",
943
  "id": "d78435d142bd5cf6704da62c778795c5",
944
  "important_keywords": []
 
883
 
884
  ---
885
 
886
+ ## CHUNK MANAGEMENT WITHIN DATASET
887
+
888
+ ---
889
+
890
  ### Add chunk
891
 
892
  **POST** `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks`
 
940
  "content": "ragflow content",
941
  "create_time": "2024-10-16 08:05:04",
942
  "create_timestamp": 1729065904.581025,
943
+ "dataset_id": "c7ee74067a2c11efb21c0242ac120006",
 
 
944
  "document_id": "5c5999ec7be811ef9cab0242ac120005",
945
  "id": "d78435d142bd5cf6704da62c778795c5",
946
  "important_keywords": []
docs/references/python_api_reference.md CHANGED
@@ -1,4 +1,4 @@
1
- from scipy.special import kwargs---
2
  sidebar_position: 2
3
  slug: /python_api_reference
4
  ---
@@ -641,6 +641,10 @@ print("Async bulk parsing cancelled.")
641
 
642
  ---
643
 
 
 
 
 
644
  ### Add chunk
645
 
646
  ```python
@@ -1436,11 +1440,11 @@ The parameters in `begin` component.
1436
  #### Examples
1437
 
1438
  ```python
1439
- from ragflow_sdk import RAGFlow
1440
 
1441
  rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
1442
  AGENT_ID = "AGENT_ID"
1443
- session = create_session(AGENT_ID,rag_object)
1444
  ```
1445
 
1446
  ---
@@ -1513,11 +1517,11 @@ A list of `Chunk` objects representing references to the message, each containin
1513
  #### Examples
1514
 
1515
  ```python
1516
- from ragflow_sdk import RAGFlow,Agent
1517
 
1518
  rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
1519
  AGENT_id = "AGENT_ID"
1520
- session = Agent.create_session(AGENT_id,rag_object)
1521
 
1522
  print("\n===== Miss R ====\n")
1523
  print("Hello. What can I do for you?")
 
1
+ ---
2
  sidebar_position: 2
3
  slug: /python_api_reference
4
  ---
 
641
 
642
  ---
643
 
644
+ ## CHUNK MANAGEMENT WITHIN DATASET
645
+
646
+ ---
647
+
648
  ### Add chunk
649
 
650
  ```python
 
1440
  #### Examples
1441
 
1442
  ```python
1443
+ from ragflow_sdk import RAGFlow, Agent
1444
 
1445
  rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
1446
  AGENT_ID = "AGENT_ID"
1447
+ session = Agent.create_session(AGENT_ID, rag_object)
1448
  ```
1449
 
1450
  ---
 
1517
  #### Examples
1518
 
1519
  ```python
1520
+ from ragflow_sdk import RAGFlow, Agent
1521
 
1522
  rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
1523
  AGENT_id = "AGENT_ID"
1524
+ session = Agent.create_session(AGENT_id, rag_object)
1525
 
1526
  print("\n===== Miss R ====\n")
1527
  print("Hello. What can I do for you?")
docs/release_notes.md CHANGED
@@ -7,6 +7,39 @@ slug: /release_notes
7
 
8
  Key features, improvements and bug fixes in the latest releases.
9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ## v0.15.0
11
 
12
  Released on December 18, 2024.
 
7
 
8
  Key features, improvements and bug fixes in the latest releases.
9
 
10
+ ## v0.15.1
11
+
12
+ Released on December 25, 2024.
13
+
14
+ ### Upgrades
15
+
16
+ - Upgrades RAGFlow's document engine [Infinity](https://github.com/infiniflow/infinity) to v0.5.2.
17
+ - Enhances the log display of document parsing status.
18
+
19
+ ### Fixed issues
20
+
21
+ This release fixes the following issues:
22
+
23
+ - The `SCORE not found` and `position_int` errors returned by [Infinity](https://github.com/infiniflow/infinity).
24
+ - Slow response in question-answering and AI search due to repetitive loading of the embedding model.
25
+ - Fails to parse documents with RAPTOR.
26
+ - Using the **Table** parsing method results in information loss.
27
+ - Miscellaneous API issues.
28
+
29
+ ### Related APIs
30
+
31
+ #### HTTP APIs
32
+
33
+ Adds an optional parameter `"user_id"` to the following APIs:
34
+
35
+ - [Create session with chat assistant](https://ragflow.io/docs/dev/http_api_reference#create-session-with-chat-assistant)
36
+ - [Update chat assistant's session](https://ragflow.io/docs/dev/http_api_reference#update-chat-assistants-session)
37
+ - [List chat assistant's sessions](https://ragflow.io/docs/dev/http_api_reference#list-chat-assistants-sessions)
38
+ - [Create session with agent](https://ragflow.io/docs/dev/http_api_reference#create-session-with-agent)
39
+ - [Converse with chat assistant](https://ragflow.io/docs/dev/http_api_reference#converse-with-chat-assistant)
40
+ - [Converse with agent](https://ragflow.io/docs/dev/http_api_reference#converse-with-agent)
41
+ - [List agent sessions](https://ragflow.io/docs/dev/http_api_reference#list-agent-sessions)
42
+
43
  ## v0.15.0
44
 
45
  Released on December 18, 2024.