uipath-langchain 0.0.102__tar.gz → 0.0.104__tar.gz

{uipath_langchain-0.0.102 → uipath_langchain-0.0.104}/PKG-INFO

@@ -1,9 +1,10 @@
 Metadata-Version: 2.4
 Name: uipath-langchain
-Version: 0.0.102
+Version: 0.0.104
 Summary: UiPath Langchain
 Project-URL: Homepage, https://uipath.com
 Project-URL: Repository, https://github.com/UiPath/uipath-langchain-python
+Project-URL: Documentation, https://uipath.github.io/uipath-python/
 Maintainer-email: Marius Cosareanu <marius.cosareanu@uipath.com>, Cristian Pufu <cristian.pufu@uipath.com>
 License-File: LICENSE
 Classifier: Development Status :: 3 - Alpha
@@ -23,9 +24,7 @@ Requires-Dist: langgraph>=0.2.70
 Requires-Dist: openai>=1.65.5
 Requires-Dist: pydantic-settings>=2.6.0
 Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: requests>=2.23.3
-Requires-Dist: types-requests>=2.32.0.20241016
-Requires-Dist: uipath<2.1.0,>=2.0.31
+Requires-Dist: uipath<2.1.0,>=2.0.33
 Provides-Extra: langchain
 Description-Content-Type: text/markdown
 
@@ -34,16 +33,18 @@ Description-Content-Type: text/markdown
 [![PyPI downloads](https://img.shields.io/pypi/dm/uipath-langchain.svg)](https://pypi.org/project/uipath-langchain/)
 [![Python versions](https://img.shields.io/pypi/pyversions/uipath-langchain.svg)](https://pypi.org/project/uipath-langchain/)
 
-A Python SDK that enables developers to build and deploy LangGraph agents to the UiPath Platform. This package provides programmatic interaction with UiPath Platform services and human-in-the-loop (HITL) semantics through Action Center integration.
+A Python SDK that enables developers to build and deploy LangGraph agents to the UiPath Cloud Platform. This package provides programmatic interaction with UiPath Cloud Platform services and human-in-the-loop (HITL) semantics through Action Center integration.
 
 This package is an extension to the [UiPath Python SDK](https://github.com/UiPath/uipath-python).
 
-This [quickstart guide](docs/quick_start.md) walks you through deploying your first agent to UiPath Cloud Platform.
+This [quickstart guide](https://uipath.github.io/uipath-python/) walks you through deploying your first agent to UiPath Cloud Platform.
+
+Check out these [sample projects](https://github.com/UiPath/uipath-langchain-python/tree/main/samples) to see the SDK in action.
 
 ## Requirements
 
-- Python 3.10 or higher
-- UiPath Automation Cloud account
+-   Python 3.10 or higher
+-   UiPath Automation Cloud account
 
 ## Installation
 
@@ -105,10 +106,12 @@ uipath pack
 Packages your project into a `.nupkg` file that can be deployed to UiPath.
 
 **Note:** Your `pyproject.toml` must include:
-- A description field (avoid characters: &, <, >, ", ', ;)
-- Author information
+
+-   A description field (avoid characters: &, <, >, ", ', ;)
+-   Author information
 
 Example:
+
 ```toml
 description = "Your package description"
 authors = [{name = "Your Name", email = "your.email@example.com"}]
@@ -125,14 +128,14 @@ Publishes the most recently created package to your UiPath Orchestrator.
 ## Project Structure
 
 To properly use the CLI for packaging and publishing, your project should include:
-- A `pyproject.toml` file with project metadata
-- A `langgraph.json` file
-- A `uipath.json` file (generated by `uipath init`)
-- Any Python files needed for your automation
+
+-   A `pyproject.toml` file with project metadata
+-   A `langgraph.json` file
+-   A `uipath.json` file (generated by `uipath init`)
+-   Any Python files needed for your automation
 
 ## Development
 
 ### Setting Up a Development Environment
 
-Please read our [contribution guidelines](CONTRIBUTING.md) before submitting a pull request.
-
+Please read our [contribution guidelines](https://github.com/UiPath/uipath-langchain-python/blob/main/CONTRIBUTING.md) before submitting a pull request.

{uipath_langchain-0.0.102 → uipath_langchain-0.0.104}/README.md

@@ -3,16 +3,18 @@
 [![PyPI downloads](https://img.shields.io/pypi/dm/uipath-langchain.svg)](https://pypi.org/project/uipath-langchain/)
 [![Python versions](https://img.shields.io/pypi/pyversions/uipath-langchain.svg)](https://pypi.org/project/uipath-langchain/)
 
-A Python SDK that enables developers to build and deploy LangGraph agents to the UiPath Platform. This package provides programmatic interaction with UiPath Platform services and human-in-the-loop (HITL) semantics through Action Center integration.
+A Python SDK that enables developers to build and deploy LangGraph agents to the UiPath Cloud Platform. This package provides programmatic interaction with UiPath Cloud Platform services and human-in-the-loop (HITL) semantics through Action Center integration.
 
 This package is an extension to the [UiPath Python SDK](https://github.com/UiPath/uipath-python).
 
-This [quickstart guide](docs/quick_start.md) walks you through deploying your first agent to UiPath Cloud Platform.
+This [quickstart guide](https://uipath.github.io/uipath-python/) walks you through deploying your first agent to UiPath Cloud Platform.
+
+Check out these [sample projects](https://github.com/UiPath/uipath-langchain-python/tree/main/samples) to see the SDK in action.
 
 ## Requirements
 
-- Python 3.10 or higher
-- UiPath Automation Cloud account
+-   Python 3.10 or higher
+-   UiPath Automation Cloud account
 
 ## Installation
 
@@ -74,10 +76,12 @@ uipath pack
 Packages your project into a `.nupkg` file that can be deployed to UiPath.
 
 **Note:** Your `pyproject.toml` must include:
-- A description field (avoid characters: &, <, >, ", ', ;)
-- Author information
+
+-   A description field (avoid characters: &, <, >, ", ', ;)
+-   Author information
 
 Example:
+
 ```toml
 description = "Your package description"
 authors = [{name = "Your Name", email = "your.email@example.com"}]
@@ -94,14 +98,14 @@ Publishes the most recently created package to your UiPath Orchestrator.
 ## Project Structure
 
 To properly use the CLI for packaging and publishing, your project should include:
-- A `pyproject.toml` file with project metadata
-- A `langgraph.json` file
-- A `uipath.json` file (generated by `uipath init`)
-- Any Python files needed for your automation
+
+-   A `pyproject.toml` file with project metadata
+-   A `langgraph.json` file
+-   A `uipath.json` file (generated by `uipath init`)
+-   Any Python files needed for your automation
 
 ## Development
 
 ### Setting Up a Development Environment
 
-Please read our [contribution guidelines](CONTRIBUTING.md) before submitting a pull request.
-
+Please read our [contribution guidelines](https://github.com/UiPath/uipath-langchain-python/blob/main/CONTRIBUTING.md) before submitting a pull request.

{uipath_langchain-0.0.102 → uipath_langchain-0.0.104}/docs/chat_models.md

@@ -1,91 +1,92 @@
-# UiPath chat models
-
-UiPath provides two chat models `UiPathAzureChatOpenAI` and `UiPathChat`. These are compatible with langgraph as drop in replacements. You do not need to add tokens from OpenAI or Anthropic, usage of these chat models will consume `AI Units` on your account.
-
-## UiPathAzureChatOpenAI
-
-`UiPathAzureChatOpenAI` can be used as a drop in replacement for `ChatOpenAI` or `AzureChatOpenAI`. 
-
-### Example usage
-
-Here is a code that is using `ChatOpenAI`
-```python
-from langchain_openai import ChatOpenAI
-
-llm = ChatOpenAI(
-    model="gpt-4o",
-    temperature=0,
-    max_tokens=4000,
-    timeout=30,
-    max_retries=2,
-    # api_key="...",  # if you prefer to pass api key in directly instaed of using env vars
-    # base_url="...",
-    # organization="...",
-    # other params...
-)
-```
-
-You can simply change `ChatOpenAi` with `UiPathAzureChatOpenAI`, you don't have to provide an `OPEN_AI_TOKEN`
-
-
-```python
-from uipath_langchain.chat.models import UiPathAzureChatOpenAI
-
-llm = UiPathAzureChatOpenAI(
-    model="gpt-4o-2024-08-06",
-    temperature=0,
-    max_tokens=4000,
-    timeout=30,
-    max_retries=2,
-    # other params...
-)
-```
-
-Currently the following models can be used with `UiPathAzureChatOpenAI` (this list can be updated in the future): 
-- `gpt-4`, `gpt-4-1106-Preview`, `gpt-4-32k`, `gpt-4-turbo-2024-04-09`, `gpt-4-vision-preview`, `gpt-4o-2024-05-13`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `o3-mini-2025-01-31`
-
-
-## UiPathChat
-
-`UiPathChat` is a more versatile clas that can suport models from diferent vendors including OpenAI.
-
-### Example usage
-
-Given the following code:
-
-```python
-from langchain_anthropic import ChatAnthropic
-
-llm = ChatAnthropic(
-    model="claude-3-5-sonnet-20240620",
-    temperature=0,
-    max_tokens=1024,
-    timeout=None,
-    max_retries=2,
-    # other params...
-)
-```
-
-You can replace it with `UiPathChat` like so:
-
-```python
-from uipath_langchain.chat.models import UiPathChat
-
-llm = UiPathChat(
-    model="anthropic.claude-3-opus-20240229-v1:0",
-    temperature=0,
-    max_tokens=1024,
-    timeout=None,
-    max_retries=2,
-    # other params...
-)
-```
-
-Currently the following models can be used with `UiPathChat` (this list can be updated in the future): 
-- `anthropic.claude-3-5-sonnet-20240620-v1:0`, `anthropic.claude-3-5-sonnet-20241022-v2:0`, `anthropic.claude-3-7-sonnet-20250219-v1:0`, `anthropic.claude-3-haiku-20240307-v1:0`, `gemini-1.5-pro-001`, `gemini-2.0-flash-001`, `gpt-4o-2024-05-13`, `gpt-4o-2024-08-06`, `gpt-4o-2024-11-20`, `gpt-4o-mini-2024-07-18`, `o3-mini-2025-01-31`
-
-### Note 
-
-Please note that that you may get errors related to data residency, as some models are not available on all regions.
-
-Example: `[Enforced Region] No model configuration found for product uipath-python-sdk in EU using model anthropic.claude-3-opus-20240229-v1:0`.
+# Chat Models
+
+UiPath provides two chat models `UiPathAzureChatOpenAI` and `UiPathChat`. These are compatible with langgraph as drop in replacements. You do not need to add tokens from OpenAI or Anthropic, usage of these chat models will consume `AI Units` on your account.
+
+## UiPathAzureChatOpenAI
+
+`UiPathAzureChatOpenAI` can be used as a drop in replacement for `ChatOpenAI` or `AzureChatOpenAI`.
+
+### Example usage
+
+Here is a code that is using `ChatOpenAI`
+
+```python
+from langchain_openai import ChatOpenAI
+
+llm = ChatOpenAI(
+    model="gpt-4o",
+    temperature=0,
+    max_tokens=4000,
+    timeout=30,
+    max_retries=2,
+    # api_key="...",  # if you prefer to pass api key in directly instead of using env vars
+    # base_url="...",
+    # organization="...",
+    # other params...
+)
+```
+
+You can simply change `ChatOpenAi` with `UiPathAzureChatOpenAI`, you don't have to provide an `OPEN_AI_TOKEN`
+
+```python
+from uipath_langchain.chat.models import UiPathAzureChatOpenAI
+
+llm = UiPathAzureChatOpenAI(
+    model="gpt-4o-2024-08-06",
+    temperature=0,
+    max_tokens=4000,
+    timeout=30,
+    max_retries=2,
+    # other params...
+)
+```
+
+Currently the following models can be used with `UiPathAzureChatOpenAI` (this list can be updated in the future):
+
+-   `gpt-4`, `gpt-4-1106-Preview`, `gpt-4-32k`, `gpt-4-turbo-2024-04-09`, `gpt-4-vision-preview`, `gpt-4o-2024-05-13`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `o3-mini-2025-01-31`
+
+## UiPathChat
+
+`UiPathChat` is a more versatile clas that can suport models from diferent vendors including OpenAI.
+
+### Example usage
+
+Given the following code:
+
+```python
+from langchain_anthropic import ChatAnthropic
+
+llm = ChatAnthropic(
+    model="claude-3-5-sonnet-20240620",
+    temperature=0,
+    max_tokens=1024,
+    timeout=None,
+    max_retries=2,
+    # other params...
+)
+```
+
+You can replace it with `UiPathChat` like so:
+
+```python
+from uipath_langchain.chat.models import UiPathChat
+
+llm = UiPathChat(
+    model="anthropic.claude-3-opus-20240229-v1:0",
+    temperature=0,
+    max_tokens=1024,
+    timeout=None,
+    max_retries=2,
+    # other params...
+)
+```
+
+Currently the following models can be used with `UiPathChat` (this list can be updated in the future):
+
+-   `anthropic.claude-3-5-sonnet-20240620-v1:0`, `anthropic.claude-3-5-sonnet-20241022-v2:0`, `anthropic.claude-3-7-sonnet-20250219-v1:0`, `anthropic.claude-3-haiku-20240307-v1:0`, `gemini-1.5-pro-001`, `gemini-2.0-flash-001`, `gpt-4o-2024-05-13`, `gpt-4o-2024-08-06`, `gpt-4o-2024-11-20`, `gpt-4o-mini-2024-07-18`, `o3-mini-2025-01-31`
+
+### Note
+
+Please note that that you may get errors related to data residency, as some models are not available on all regions.
+
+Example: `[Enforced Region] No model configuration found for product uipath-python-sdk in EU using model anthropic.claude-3-opus-20240229-v1:0`.

{uipath_langchain-0.0.102 → uipath_langchain-0.0.104}/docs/context_grounding.md

@@ -1,90 +1,91 @@
-# Context Grounding
-
-Context Grounding Service allows you to:
-- Search through indexed documents using natural language queries
-- Ground LLM responses in your organization's specific information
-- Retrieve context-relevant documents for various applications
-
-
-You will need to create an index in `Context Grounding` to use this feature. To create an index go to organization `Admin` -> `AI Trust Layer` -> `Context Grounding`. There you can create a new index and add documents to it. See the full documentation [here](https://docs.uipath.com/automation-cloud/automation-cloud/latest/admin-guide/about-context-grounding) for more details.
-
-
-# ContextGroundingRetriever
-
-The `ContextGroundingRetriever` is a document retrieval system that uses vector search to efficiently find and retrieve relevant information from your document store.
-
-## Basic Usage
-
-Create a simple retriever by specifying an index name:
-
-```python
-from uipath_langchain.retrievers import ContextGroundingRetriever
-
-retriever = ContextGroundingRetriever(index_name = "Company Policy Context")
-print(retriever.invoke("What is the company policy on remote work?"))
-```
-
-## Integration with LangChain Tools
-
-You can easily integrate the retriever with LangChain's tool system:
-
-```python
-from langchain.agents import create_react_agent
-from langchain.tools.retriever import create_retriever_tool
-from uipath_langchain.retrievers import ContextGroundingRetriever
-
-retriever = ContextGroundingRetriever(index_name = "Company Policy Context")
-retriever_tool = create_retriever_tool(
-    retriever,
-    "ContextforInvoiceDisputeInvestigation",
-   """
-   Use this tool to search the company internal documents for information about policies around dispute resolution.
-   Use a meaningful query to load relevant information from the documents. Save the citation for later use.
-   """
-)
-
-# You can use the tool in your agents
-model = OpenAI()
-tools = [retriever_tool]
-agent = create_react_agent(model, tools, prompt="Answer user questions as best as you can using the search tool.")
-```
-
-
-## Advanced Usage
-
-For complex applications, the retriever can be combined with other LangChain components to create robust document QA systems, agents, or knowledge bases.
-
-
-
-# ContextGroundingVectorStore
-
-`ContextGroundingVectorStore` is a vector store implementation designed for context-aware document retrieval. It allows you to perform semantic searches and create retrieval chains with language models.
-
-## Searching Documents
-
-The vector store supports various search methods:
-
-```python
-from uipath_langchain.vectorstores.context_grounding_vectorstore import ContextGroundingVectorStore
-
-vectorstore = ContextGroundingVectorStore(index_name="Company policy")
-
-# Perform semantic searches with distance scores
-docs_with_scores = vectorstore.asimilarity_search_with_score(query="What is the company policy on data storage?", k=5)
-
-# Perform a similarity search with relevance scores
-docs_with_relevance_scores = await vectorstore.asimilarity_search_with_relevance_scores(query=query, k=5)
-```
-
-## Creating a Retrieval Chain
-
-You can integrate the vector store into a retrieval chain with a language model:
-
-```python
-# Run a retrieval chain
-model = UiPathAzureChatOpenAI(model="gpt-4o-2024-08-06", max_retries=3)
-retrieval_chain = create_retrieval_chain(vectorstore=vectorstore, model=model)
-
-query = "What is the ECCN for a laptop?"
-result = retrieval_chain(query)
+# Context Grounding
+
+Context Grounding Service allows you to:
+
+- Search through indexed documents using natural language queries
+- Ground LLM responses in your organization's specific information
+- Retrieve context-relevant documents for various applications
+
+
+You will need to create an index in `Context Grounding` to use this feature. To create an index go to organization `Admin` -> `AI Trust Layer` -> `Context Grounding`. There you can create a new index and add documents to it. See the full documentation [here](https://docs.uipath.com/automation-cloud/automation-cloud/latest/admin-guide/about-context-grounding) for more details.
+
+
+## ContextGroundingRetriever
+
+The `ContextGroundingRetriever` is a document retrieval system that uses vector search to efficiently find and retrieve relevant information from your document store.
+
+### Basic Usage
+
+Create a simple retriever by specifying an index name:
+
+```python
+from uipath_langchain.retrievers import ContextGroundingRetriever
+
+retriever = ContextGroundingRetriever(index_name = "Company Policy Context")
+print(retriever.invoke("What is the company policy on remote work?"))
+```
+
+### Integration with LangChain Tools
+
+You can easily integrate the retriever with LangChain's tool system:
+
+```python
+from langchain.agents import create_react_agent
+from langchain.tools.retriever import create_retriever_tool
+from uipath_langchain.retrievers import ContextGroundingRetriever
+
+retriever = ContextGroundingRetriever(index_name = "Company Policy Context")
+retriever_tool = create_retriever_tool(
+    retriever,
+    "ContextforInvoiceDisputeInvestigation",
+   """
+   Use this tool to search the company internal documents for information about policies around dispute resolution.
+   Use a meaningful query to load relevant information from the documents. Save the citation for later use.
+   """
+)
+
+# You can use the tool in your agents
+model = OpenAI()
+tools = [retriever_tool]
+agent = create_react_agent(model, tools, prompt="Answer user questions as best as you can using the search tool.")
+```
+
+
+### Advanced Usage
+
+For complex applications, the retriever can be combined with other LangChain components to create robust document QA systems, agents, or knowledge bases.
+
+
+
+## ContextGroundingVectorStore
+
+`ContextGroundingVectorStore` is a vector store implementation designed for context-aware document retrieval. It allows you to perform semantic searches and create retrieval chains with language models.
+
+### Searching Documents
+
+The vector store supports various search methods:
+
+```python
+from uipath_langchain.vectorstores.context_grounding_vectorstore import ContextGroundingVectorStore
+
+vectorstore = ContextGroundingVectorStore(index_name="Company policy")
+
+# Perform semantic searches with distance scores
+docs_with_scores = vectorstore.asimilarity_search_with_score(query="What is the company policy on data storage?", k=5)
+
+# Perform a similarity search with relevance scores
+docs_with_relevance_scores = await vectorstore.asimilarity_search_with_relevance_scores(query=query, k=5)
+```
+
+### Creating a Retrieval Chain
+
+You can integrate the vector store into a retrieval chain with a language model:
+
+```python
+# Run a retrieval chain
+model = UiPathAzureChatOpenAI(model="gpt-4o-2024-08-06", max_retries=3)
+retrieval_chain = create_retrieval_chain(vectorstore=vectorstore, model=model)
+
+query = "What is the ECCN for a laptop?"
+result = retrieval_chain(query)
 ```

{uipath_langchain-0.0.102 → uipath_langchain-0.0.104}/docs/human_in_the_loop.md

@@ -4,10 +4,8 @@ Guide for **Human-In-The-Loop** scenarios within the UiPath-Langchain integratio
 It focuses on the **interrupt(model)** functionality, illustrating its role as a symbolic representation of an agent's
 wait state within the Langchain framework.
 
-
 ## Models Overview
 
-
 ### 1. CreateAction
 
 The `CreateAction` model is utilized to create an escalation action within the UiPath Action Center as part of an interrupt context. The action will rely on a previously created UiPath app.
@@ -15,18 +13,21 @@ After addressing the escalation, the current agent will resume execution.
 For more information on UiPath apps, refer to the [UiPath Apps User Guide](https://docs.uipath.com/apps/automation-cloud/latest/user-guide/introduction).
 
 #### Attributes:
-- **name** (Optional[str]): The name of the app.
-- **key** (Optional[str]): The key of the app.
-- **title** (str): The title of the action to create.
-- **data** (Optional[Dict[str, Any]]): Values that the action will be populated with.
-- **app_version** (Optional[int]): The version of the app (defaults to 1).
-- **assignee** (Optional[str]): The username or email of the person assigned to handle the escalation.
+
+-   **name** (Optional[str]): The name of the app.
+-   **key** (Optional[str]): The key of the app.
+-   **title** (str): The title of the action to create.
+-   **data** (Optional[Dict[str, Any]]): Values that the action will be populated with.
+-   **app_version** (Optional[int]): The version of the app (defaults to 1).
+-   **assignee** (Optional[str]): The username or email of the person assigned to handle the escalation.
 
 #### Example:
+
 ```python
 from uipath.models import CreateAction
 action_output = interrupt(CreateAction(name="AppName", title="Escalate Issue", data={"key": "value"}, app_version=1, assignee="user@example.com"))
 ```
+
 For a practical implementation of the `CreateAction` model, refer to the [ticket-classification sample](https://github.com/UiPath/uipath-langchain-python/tree/main/samples/ticket-classification). This sample demonstrates how to create an action with dynamic input.
 
 ---
@@ -36,14 +37,18 @@ For a practical implementation of the `CreateAction` model, refer to the [ticket
 The `WaitAction` model is used to wait for an action to be handled. This model is intended for scenarios where the action has already been created.
 
 #### Attributes:
-- **action** (Action): The instance of the action to wait for.
+
+-   **action** (Action): The instance of the action to wait for.
 
 #### Example:
+
 ```python
 from uipath.models import WaitAction
 action_output = interrupt(WaitAction(action=my_action_instance))
 ```
+
 ---
+
 > 💡 UiPath Langchain sdk also supports **Robot/Agent-in-the-loop** scenarios. In this context, the execution of one agent
 > can be suspended until another robot or agent finishes its execution.
 
@@ -54,10 +59,12 @@ This process can be of various types, including API workflows, Agents or RPA aut
 Upon completion of the invoked process, the current agent will automatically resume execution.
 
 #### Attributes:
-- **name** (str): The name of the process to invoke.
-- **input_arguments** (Optional[Dict[str, Any]]): A dictionary containing the input arguments required for the invoked process.
+
+-   **name** (str): The name of the process to invoke.
+-   **input_arguments** (Optional[Dict[str, Any]]): A dictionary containing the input arguments required for the invoked process.
 
 #### Example:
+
 ```python
 from uipath.models import InvokeProcess
 process_output = interrupt(InvokeProcess(name="MyProcess", input_arguments={"arg1": "value1"}))
@@ -70,14 +77,15 @@ For a practical implementation of the `InvokeProcess` model, refer to the [multi
 ### 4. WaitJob
 
 The `WaitJob` model is used to wait for a job completion. Unlike `InvokeProcess`, which automatically creates a job, this model is intended for scenarios where
-    the job has already been created.
+the job has already been created.
 
 #### Attributes:
-- **job** (Job): The instance of the job that the agent will wait for. This should be a valid job object that has been previously created.
+
+-   **job** (Job): The instance of the job that the agent will wait for. This should be a valid job object that has been previously created.
 
 #### Example:
+
 ```python
 from uipath.models import WaitJob
 job_output = interrupt(WaitJob(job=my_job_instance))
 ```
-