uipath-langchain 0.0.103__tar.gz → 0.0.104__tar.gz

{uipath_langchain-0.0.103 → uipath_langchain-0.0.104}/PKG-INFO

@@ -1,9 +1,10 @@
 Metadata-Version: 2.4
 Name: uipath-langchain
-Version: 0.0.103
+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
@@ -23,8 +24,6 @@ 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,>=2.0.33
 Provides-Extra: langchain
 Description-Content-Type: text/markdown

{uipath_langchain-0.0.103 → uipath_langchain-0.0.104}/docs/chat_models.md

@@ -1,4 +1,4 @@
-# UiPath Chat Models
+# 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.
 

{uipath_langchain-0.0.103 → 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-0.0.103 → uipath_langchain-0.0.104}/docs/quick_start.md

@@ -2,11 +2,11 @@
 
 ## Introduction
 
-This guide walks you through the process of setting up, creating, publishing, and running your first UiPath-LangChain Agent.
+This guide provides step-by-step instructions for setting up, creating, publishing, and running your first UiPath-LangChain Agent.
 
 ## Prerequisites
 
-Ensure you have the following installed before proceeding:
+Before proceeding, ensure you have the following installed:
 
 -   Python 3.10 or higher
 -   `pip` or `uv` package manager
@@ -17,13 +17,10 @@ Ensure you have the following installed before proceeding:
 
 1. **Anthropic** - Generate an Anthropic API key [here](https://console.anthropic.com/settings/keys).
 
-2. **OpenAi** - Generate an OpenAI API key [here](https://platform.openai.com).
+2. **OpenAI** - Generate an OpenAI API key [here](https://platform.openai.com).
+   ///
 
-///
-
-## Step-by-Step Guide
-
-## Creating a New Project
+## Creating A New Project
 
 We recommend using `uv` for package management. To create a new project:
 
@@ -66,7 +63,7 @@ Creating virtual environment at: .venv
 Activate with: source .venv/bin/activate
 
 # Activate the virtual environment
-# For Windows PowerShell: .venv\Scripts\Activate.ps1
+# For Windows PowerShell/ Windows CMD: .venv\Scripts\activate
 # For Windows Bash: source .venv/Scripts/activate
 > source .venv/bin/activate
 
@@ -74,7 +71,7 @@ Activate with: source .venv/bin/activate
 > uv add uipath-langchain
 
 # Verify the uipath installation
-> uipath --lv
+> uipath -lv
 uipath-langchain version 0.0.100
 ```
 
@@ -100,7 +97,7 @@ uipath-langchain version 0.0.100
 > pip install uipath-langchain
 
 # Verify the uipath installation
-> uipath --lv
+> uipath -lv
 uipath-langchain version 0.0.100
 ```
 
@@ -108,7 +105,7 @@ uipath-langchain version 0.0.100
 
 ## Create Your First UiPath Agent
 
-Generate your first UiPath LangChain:
+Generate your first UiPath LangChain agent:
 
 <!-- termynal -->
 
@@ -137,19 +134,17 @@ This command creates the following files:
 | ---------------- | --------------------------------------------------------------------------------------------------------------------------------- |
 | `.env`           | Environment variables and secrets (this file will not be packed & published).                                                     |
 | `main.py`        | LangGraph agent code.                                                                                                             |
-| `uipath.json`    | Input/output json schemas and bindings.                                                                                           |
+| `uipath.json`    | Input/output JSON schemas and bindings.                                                                                           |
 | `langgraph.json` | [LangGraph](https://langchain-ai.github.io/langgraph/concepts/application_structure/#file-structure) specific configuration file. |
 | `agent.mermaid`  | Graph visual representation.                                                                                                      |
 
 ## Set Up Environment Variables
 
-Before running the agent, set either `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` in the previously created `.env` file:
+Before running the agent, configure either `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` in the `.env` file:
 
 //// tab | Open AI
 
-```hl_lines="3"
-UIPATH_ACCESS_TOKEN=YOUR_TOKEN_HERE
-UIPATH_URL=https://cloud.uipath.com/ACCOUNT_NAME/TENANT_NAME
+```
 OPENAI_API_KEY=sk-proj-......
 ```
 
@@ -157,15 +152,29 @@ OPENAI_API_KEY=sk-proj-......
 
 //// tab | ANTHROPIC_API_KEY
 
-```hl_lines="3"
-UIPATH_ACCESS_TOKEN=YOUR_TOKEN_HERE
-UIPATH_URL=https://cloud.uipath.com/ACCOUNT_NAME/TENANT_NAME
-ANTHROPIC_API_KEY=your_api_key_here
+```
+ANTHROPIC_API_KEY=sk-ant-a.....
 ```
 
 ////
 
-## Run the Agent Locally
+## Authenticate With UiPath
+
+<!-- termynal -->
+
+```shell
+> uipath auth
+⠋ Authenticating with UiPath ...
+🔗 If a browser window did not open, please open the following URL in your browser: [LINK]
+👇 Select tenant:
+  0: Tenant1
+  1: Tenant2
+Select tenant number: 0
+Selected tenant: Tenant1
+✓  Authentication successful.
+```
+
+## Run The Agent Locally
 
 Execute the agent with a sample input:
 
@@ -177,35 +186,51 @@ Execute the agent with a sample input:
 [2025-04-29 12:32:07,689][INFO] ((), {'topic': 'UiPath', 'report': "..."})
 ```
 
-This command runs your agent locally and generates the report at standard output.
-
-## Pack and Publish the agent on UiPath Cloud Platform
+This command runs your agent locally and displays the report in the standard output.
 
-Follow these steps to publish and run your agent on UiPath Cloud Platform:
+/// warning
+Depending on the shell you are using, it may be necessary to escape the input json:
 
-### Authenticate with UiPath
+/// tab | Bash/ZSH/PowerShell
+```console
+uipath run agent '{"topic": "UiPath"}'
+```
+///
 
-<!-- termynal -->
+/// tab | Windows CMD
+```console
+uipath run agent "{""topic"": ""UiPath""}"
+```
+///
 
-```shell
-> uipath auth
-⠋ Authenticating with UiPath ...
-🔗 If a browser window did not open, please open the following URL in your browser: [LINK]
-👇 Select tenant:
-  0: Tenant1
-  1: Tenant2
-Select tenant number: 0
-Selected tenant: Tenant1
-✓  Authentication successful.
+/// tab | Windows PowerShell
+```console
+uipath run agent '{\"topic\":\"uipath\"}'
 ```
+///
+
+///
+
+/// info
+
+Run command also accepts a _.json_ file as input:
+>uipath run agent -f <path_to_input_json_file>
 
-### (Optional) Update author details in `pyproject.toml`
+   ///
+
+## Deploy The Agent On UiPath Cloud Platform
+
+Follow these steps to publish and run your agent on UiPath Cloud Platform:
+
+### (Optional) Customize The Package
+
+Update author details in `pyproject.toml`:
 
 ```toml
 authors = [{ name = "Your Name", email = "your.name@example.com" }]
 ```
 
-### Package your project:
+### Package Your Project
 
 <!-- termynal -->
 
@@ -219,7 +244,7 @@ Authors    : Your Name
 ✓  Project successfully packaged.
 ```
 
-### Publish to your workspace
+### Publish To My Workspace
 
 <!-- termynal -->
 
@@ -234,13 +259,19 @@ Authors    : Your Name
 
 > Please note that a process will be auto-created only upon publishing to **my-workspace** package feed.
 
-### Configure environment variables using the provided link
-
-![Set Environment Variables](quick_start_images/cloud_env_var.png)
+Set the environment variables using the provided link:
 
-## Invoke the Agent on UiPath Cloud Platform
+<picture data-light="quick_start_images/cloud_env_var_light.png" data-dark="quick_start_images/cloud_env_var_dark.png">
+  <source
+    media="(prefers-color-scheme: dark)"
+    srcset="quick_start_images/cloud_env_var_dark.png"
+  />
+  <img
+    src="quick_start_images/cloud_env_var_light.png"
+  />
+</picture>
 
-Invoke the agent in UiPath Cloud Platform:
+## Invoke The Agent On UiPath Cloud Platform
 
 <!-- termynal -->
 
@@ -254,7 +285,17 @@ Invoke the agent in UiPath Cloud Platform:
 
 Use the provided link to monitor your job and view detailed traces.
 
-## Next steps
+<picture data-light="quick_start_images/invoke_output_light.png" data-dark="quick_start_images/invoke_output_dark.png">
+  <source
+    media="(prefers-color-scheme: dark)"
+    srcset="quick_start_images/invoke_output_dark.png"
+  />
+  <img
+    src="quick_start_images/invoke_output_light.png"
+  />
+</picture>
+
+## Next Steps
 
 Congratulations! You have successfully set up, created, published, and run a UiPath LangChain Agent. 🚀
 

{uipath_langchain-0.0.103 → uipath_langchain-0.0.104}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "uipath-langchain"
-version = "0.0.103"
+version = "0.0.104"
 description = "UiPath Langchain"
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.10"
@@ -12,8 +12,6 @@ dependencies = [
     "langchain-community>=0.3.21",
     "langchain-openai>=0.3.3",
     "langchain>=0.3.4",
-    "requests>=2.23.3",
-    "types-requests>=2.32.0.20241016",
     "pydantic-settings>=2.6.0",
     "python-dotenv>=1.0.1",
     "httpx>=0.27.0",
@@ -38,6 +36,7 @@ register = "uipath_langchain.middlewares:register_middleware"
 [project.urls]
 Homepage = "https://uipath.com"
 Repository = "https://github.com/UiPath/uipath-langchain-python"
+Documentation = "https://uipath.github.io/uipath-python/"
 
 [build-system]
 requires = ["hatchling"]