vectara-agentic 0.1.2__tar.gz → 0.1.4__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of vectara-agentic might be problematic. Click here for more details.

Files changed (22) hide show
  1. {vectara_agentic-0.1.2/vectara_agentic.egg-info → vectara_agentic-0.1.4}/PKG-INFO +11 -7
  2. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/README.md +4 -5
  3. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/setup.py +9 -2
  4. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4/vectara_agentic.egg-info}/PKG-INFO +11 -7
  5. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/LICENSE +0 -0
  6. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/MANIFEST.in +0 -0
  7. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/requirements.txt +0 -0
  8. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/setup.cfg +0 -0
  9. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/tests/test_agent.py +0 -0
  10. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/tests/test_tools.py +0 -0
  11. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/__init__.py +0 -0
  12. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/_callback.py +0 -0
  13. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/_prompts.py +0 -0
  14. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/agent.py +0 -0
  15. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/tools.py +0 -0
  16. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/tools_catalog.py +0 -0
  17. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/types.py +0 -0
  18. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic/utils.py +0 -0
  19. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/SOURCES.txt +0 -0
  20. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/dependency_links.txt +0 -0
  21. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/requires.txt +0 -0
  22. {vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/top_level.txt +0 -0
{vectara_agentic-0.1.2/vectara_agentic.egg-info → vectara_agentic-0.1.4}/PKG-INFO RENAMED
@@ -1,13 +1,18 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: vectara_agentic
3
- Version: 0.1.2
3
+ Version: 0.1.4
4
4
  Summary: A Python package for creating AI Assistants and AI Agents with Vectara
5
5
  Home-page: https://github.com/vectara/py-vectara-agentic
6
6
  Author: Ofer Mendelevitch
7
7
  Author-email: ofer@vectara.com
8
+ Project-URL: Documentation, https://vectara.github.io/vectara-agentic-docs/
9
+ Keywords: LLM,NLP,RAG,Agentic-RAG
8
10
  Classifier: Programming Language :: Python :: 3
9
- Classifier: License :: OSI Approved :: MIT License
11
+ Classifier: License :: OSI Approved :: Apache Software License
10
12
  Classifier: Operating System :: OS Independent
13
+ Classifier: Development Status :: 4 - Beta
14
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
15
+ Classifier: Topic :: Software Development :: Libraries :: Python Modules
11
16
  Requires-Python: >=3.10
12
17
  Description-Content-Type: text/markdown
13
18
  License-File: LICENSE
@@ -42,7 +47,7 @@ Requires-Dist: python-dotenv==1.0.1
42
47
  [![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.com/invite/GFb8gMz6UH)
43
48
 
44
49
 
45
- The idea of LLM-based agents it to use the LLM for building sophisticated AI assistants:
50
+ The idea of LLM-based agents is to use the LLM for building sophisticated AI assistants:
46
51
  - The LLM is used for reasoning and coming up with a game-plan for how to respond to the user query.
47
52
  - There are 1 or more "tools" provided to the agent. These tools can be used by the LLM to execute its plan.
48
53
 
@@ -61,7 +66,7 @@ The idea of LLM-based agents it to use the LLM for building sophisticated AI ass
61
66
 
62
67
  ### Install vectara-agentic
63
68
 
64
- - `python -m pip install vectara-agentic`
69
+ - `pip install vectara-agentic`
65
70
 
66
71
  ### Create your AI assistant
67
72
 
@@ -76,7 +81,7 @@ vec_factory = VectaraToolFactory(vectara_api_key=os.environ['VECTARA_API_KEY'],
76
81
  vectara_customer_id=os.environ['VECTARA_CUSTOMER_ID'],
77
82
  vectara_corpus_id=os.environ['VECTARA_CORPUS_ID'])
78
83
  ```
79
- The tools factory has a useful helper function called `create_rag_tool` which automates the creation of a
84
+ The Vectara tool factory has a useful helper function called `create_rag_tool` which automates the creation of a
80
85
  tool to query Vectara RAG.
81
86
 
82
87
  For example if my Vectara corpus includes financial information from company
@@ -106,8 +111,7 @@ this tool in the most effective way.
106
111
  The `tool_filter_template` provides the template filtering expression the tool should use when calling Vectara.
107
112
 
108
113
  You can of course create more than one Vectara tool; tools may point at different corpora or may have different parameters for search
109
- or generation. Remember though to think about your tools wisely and from the agent point of view - at the end of the day they are just tools
110
- in the service of the agent, so should be differentiated.
114
+ or generation.
111
115
 
112
116
  #### Step 2: Create Other Tools, as needed
113
117
 
{vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/README.md RENAMED
@@ -7,7 +7,7 @@
7
7
  [![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.com/invite/GFb8gMz6UH)
8
8
 
9
9
 
10
- The idea of LLM-based agents it to use the LLM for building sophisticated AI assistants:
10
+ The idea of LLM-based agents is to use the LLM for building sophisticated AI assistants:
11
11
  - The LLM is used for reasoning and coming up with a game-plan for how to respond to the user query.
12
12
  - There are 1 or more "tools" provided to the agent. These tools can be used by the LLM to execute its plan.
13
13
 
@@ -26,7 +26,7 @@ The idea of LLM-based agents it to use the LLM for building sophisticated AI ass
26
26
 
27
27
  ### Install vectara-agentic
28
28
 
29
- - `python -m pip install vectara-agentic`
29
+ - `pip install vectara-agentic`
30
30
 
31
31
  ### Create your AI assistant
32
32
 
@@ -41,7 +41,7 @@ vec_factory = VectaraToolFactory(vectara_api_key=os.environ['VECTARA_API_KEY'],
41
41
  vectara_customer_id=os.environ['VECTARA_CUSTOMER_ID'],
42
42
  vectara_corpus_id=os.environ['VECTARA_CORPUS_ID'])
43
43
  ```
44
- The tools factory has a useful helper function called `create_rag_tool` which automates the creation of a
44
+ The Vectara tool factory has a useful helper function called `create_rag_tool` which automates the creation of a
45
45
  tool to query Vectara RAG.
46
46
 
47
47
  For example if my Vectara corpus includes financial information from company
@@ -71,8 +71,7 @@ this tool in the most effective way.
71
71
  The `tool_filter_template` provides the template filtering expression the tool should use when calling Vectara.
72
72
 
73
73
  You can of course create more than one Vectara tool; tools may point at different corpora or may have different parameters for search
74
- or generation. Remember though to think about your tools wisely and from the agent point of view - at the end of the day they are just tools
75
- in the service of the agent, so should be differentiated.
74
+ or generation.
76
75
 
77
76
  #### Step 2: Create Other Tools, as needed
78
77
 
{vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/setup.py RENAMED
@@ -8,7 +8,7 @@ def read_requirements():
8
8
 
9
9
  setup(
10
10
  name="vectara_agentic",
11
- version="0.1.2",
11
+ version="0.1.4",
12
12
  author="Ofer Mendelevitch",
13
13
  author_email="ofer@vectara.com",
14
14
  description="A Python package for creating AI Assistants and AI Agents with Vectara",
@@ -19,8 +19,15 @@ setup(
19
19
  install_requires=read_requirements(),
20
20
  classifiers=[
21
21
  "Programming Language :: Python :: 3",
22
- "License :: OSI Approved :: MIT License",
22
+ "License :: OSI Approved :: Apache Software License",
23
23
  "Operating System :: OS Independent",
24
+ "Development Status :: 4 - Beta",
25
+ "Topic :: Scientific/Engineering :: Artificial Intelligence",
26
+ "Topic :: Software Development :: Libraries :: Python Modules",
24
27
  ],
28
+ keywords = ["LLM", "NLP", "RAG", "Agentic-RAG"],
29
+ project_urls={
30
+ "Documentation": "https://vectara.github.io/vectara-agentic-docs/",
31
+ },
25
32
  python_requires=">=3.10",
26
33
  )
{vectara_agentic-0.1.2 → vectara_agentic-0.1.4/vectara_agentic.egg-info}/PKG-INFO RENAMED
@@ -1,13 +1,18 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: vectara_agentic
3
- Version: 0.1.2
3
+ Version: 0.1.4
4
4
  Summary: A Python package for creating AI Assistants and AI Agents with Vectara
5
5
  Home-page: https://github.com/vectara/py-vectara-agentic
6
6
  Author: Ofer Mendelevitch
7
7
  Author-email: ofer@vectara.com
8
+ Project-URL: Documentation, https://vectara.github.io/vectara-agentic-docs/
9
+ Keywords: LLM,NLP,RAG,Agentic-RAG
8
10
  Classifier: Programming Language :: Python :: 3
9
- Classifier: License :: OSI Approved :: MIT License
11
+ Classifier: License :: OSI Approved :: Apache Software License
10
12
  Classifier: Operating System :: OS Independent
13
+ Classifier: Development Status :: 4 - Beta
14
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
15
+ Classifier: Topic :: Software Development :: Libraries :: Python Modules
11
16
  Requires-Python: >=3.10
12
17
  Description-Content-Type: text/markdown
13
18
  License-File: LICENSE
@@ -42,7 +47,7 @@ Requires-Dist: python-dotenv==1.0.1
42
47
  [![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.com/invite/GFb8gMz6UH)
43
48
 
44
49
 
45
- The idea of LLM-based agents it to use the LLM for building sophisticated AI assistants:
50
+ The idea of LLM-based agents is to use the LLM for building sophisticated AI assistants:
46
51
  - The LLM is used for reasoning and coming up with a game-plan for how to respond to the user query.
47
52
  - There are 1 or more "tools" provided to the agent. These tools can be used by the LLM to execute its plan.
48
53
 
@@ -61,7 +66,7 @@ The idea of LLM-based agents it to use the LLM for building sophisticated AI ass
61
66
 
62
67
  ### Install vectara-agentic
63
68
 
64
- - `python -m pip install vectara-agentic`
69
+ - `pip install vectara-agentic`
65
70
 
66
71
  ### Create your AI assistant
67
72
 
@@ -76,7 +81,7 @@ vec_factory = VectaraToolFactory(vectara_api_key=os.environ['VECTARA_API_KEY'],
76
81
  vectara_customer_id=os.environ['VECTARA_CUSTOMER_ID'],
77
82
  vectara_corpus_id=os.environ['VECTARA_CORPUS_ID'])
78
83
  ```
79
- The tools factory has a useful helper function called `create_rag_tool` which automates the creation of a
84
+ The Vectara tool factory has a useful helper function called `create_rag_tool` which automates the creation of a
80
85
  tool to query Vectara RAG.
81
86
 
82
87
  For example if my Vectara corpus includes financial information from company
@@ -106,8 +111,7 @@ this tool in the most effective way.
106
111
  The `tool_filter_template` provides the template filtering expression the tool should use when calling Vectara.
107
112
 
108
113
  You can of course create more than one Vectara tool; tools may point at different corpora or may have different parameters for search
109
- or generation. Remember though to think about your tools wisely and from the agent point of view - at the end of the day they are just tools
110
- in the service of the agent, so should be differentiated.
114
+ or generation.
111
115
 
112
116
  #### Step 2: Create Other Tools, as needed
113
117
 
{vectara_agentic-0.1.2 → vectara_agentic-0.1.4}/LICENSE RENAMED
File without changes