diff --git a/docker-compose.yml b/docker-compose.yml
index 67021202..daa921ae 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -100,9 +100,13 @@ services:
- LANGFLOW_LOAD_FLOWS_PATH=/app/flows
- LANGFLOW_SECRET_KEY=${LANGFLOW_SECRET_KEY}
- JWT="dummy"
+ - OWNER=None
+ - OWNER_NAME=None
+ - OWNER_EMAIL=None
+ - CONNECTOR_TYPE=system
- OPENRAG-QUERY-FILTER="{}"
- OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
- - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD
+ - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE
- LANGFLOW_LOG_LEVEL=DEBUG
- LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}
- LANGFLOW_SUPERUSER=${LANGFLOW_SUPERUSER}
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index 255b0b68..2ea5ef9f 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -38,13 +38,9 @@ The file is loaded into your OpenSearch database, and appears in the Knowledge p
To load and process a directory from the mapped location, click **Add Knowledge**, and then click **Process Folder**.
The files are loaded into your OpenSearch database, and appear in the Knowledge page.
-### Ingest files through OAuth connectors (#oauth-ingestion)
+### Ingest files through OAuth connectors {#oauth-ingestion}
-OpenRAG supports the following enterprise-grade OAuth connectors for seamless document synchronization.
-
-- **Google Drive**
-- **OneDrive**
-- **AWS**
+OpenRAG supports Google Drive, OneDrive, and AWS S3 as OAuth connectors for seamless document synchronization.
OAuth integration allows individual users to connect their personal cloud storage accounts to OpenRAG. Each user must separately authorize OpenRAG to access their own cloud storage files. When a user connects a cloud service, they are redirected to authenticate with that service provider and grant OpenRAG permission to sync documents from their personal cloud storage.
diff --git a/docs/docs/get-started/install.mdx b/docs/docs/get-started/install.mdx
index 67f4ae89..dcb5c5f1 100644
--- a/docs/docs/get-started/install.mdx
+++ b/docs/docs/get-started/install.mdx
@@ -79,8 +79,46 @@ For more information on virtual environments, see [uv](https://docs.astral.sh/uv
Command completed successfully
```
-7. To open the OpenRAG application, click **Open App** or press 6.
-8. Continue with the Quickstart.
+7. To open the OpenRAG application, click **Open App**, press 6, or navigate to `http://localhost:3000`.
+ The application opens.
+8. Select your language model and embedding model provider, and complete the required fields.
+ **Your provider can only be selected once, and you must use the same provider for your language model and embedding model.**
+ The language model can be changed, but the embeddings model cannot be changed.
+ To change your provider selection, you must restart OpenRAG and delete the `config.yml` file.
+
+
+
+ 9. If you already entered a value for `OPENAI_API_KEY` in the TUI in Step 5, enable **Get API key from environment variable**.
+ 10. Under **Advanced settings**, select your **Embedding Model** and **Language Model**.
+ 11. To load 2 sample PDFs, enable **Sample dataset**.
+ This is recommended, but not required.
+ 12. Click **Complete**.
+
+
+
+ 9. Complete the fields for **watsonx.ai API Endpoint**, **IBM API key**, and **IBM Project ID**.
+ These values are found in your IBM watsonx deployment.
+ 10. Under **Advanced settings**, select your **Embedding Model** and **Language Model**.
+ 11. To load 2 sample PDFs, enable **Sample dataset**.
+ This is recommended, but not required.
+ 12. Click **Complete**.
+
+
+
+ 9. Enter your Ollama server's base URL address.
+ The default Ollama server address is `http://localhost:11434`.
+ Since OpenRAG is running in a container, you may need to change `localhost` to access services outside of the container. For example, change `http://localhost:11434` to `http://host.docker.internal:11434` to connect to Ollama.
+ OpenRAG automatically sends a test connection to your Ollama server to confirm connectivity.
+ 10. Select the **Embedding Model** and **Language Model** your Ollama server is running.
+ OpenRAG automatically lists the available models from your Ollama server.
+ 11. To load 2 sample PDFs, enable **Sample dataset**.
+ This is recommended, but not required.
+ 12. Click **Complete**.
+
+
+
+
+13. Continue with the [Quickstart](/quickstart).
### Advanced Setup {#advanced-setup}
diff --git a/docs/docs/get-started/quickstart.mdx b/docs/docs/get-started/quickstart.mdx
index 748a8078..b071529b 100644
--- a/docs/docs/get-started/quickstart.mdx
+++ b/docs/docs/get-started/quickstart.mdx
@@ -11,7 +11,41 @@ Get started with OpenRAG by loading your knowledge, swapping out your language m
## Prerequisites
-- Install and start OpenRAG
+- [Install and start OpenRAG](/install)
+- Create a [Langflow API key](https://docs.langflow.org/api-keys-and-authentication)
+
+ Create a Langflow API key
+
+ A Langflow API key is a user-specific token you can use with Langflow.
+ It is **only** used for sending requests to the Langflow server.
+ It does **not** access to OpenRAG.
+
+ To create a Langflow API key, do the following:
+
+ 1. In Langflow, click your user icon, and then select **Settings**.
+ 2. Click **Langflow API Keys**, and then click **Add New**.
+ 3. Name your key, and then click **Create API Key**.
+ 4. Copy the API key and store it securely.
+ 5. To use your Langflow API key in a request, set a `LANGFLOW_API_KEY` environment variable in your terminal, and then include an `x-api-key` header or query parameter with your request.
+ For example:
+
+ ```bash
+ # Set variable
+ export LANGFLOW_API_KEY="sk..."
+
+ # Send request
+ curl --request POST \
+ --url "http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID" \
+ --header "Content-Type: application/json" \
+ --header "x-api-key: $LANGFLOW_API_KEY" \
+ --data '{
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "Hello"
+ }'
+ ```
+
+
## Find your way around
@@ -20,14 +54,18 @@ Get started with OpenRAG by loading your knowledge, swapping out your language m
For more information, see [Langflow Agents](/agents).
2. Ask `What documents are available to you?`
The agent responds with a message summarizing the documents that OpenRAG loads by default, which are PDFs about evaluating data quality when using LLMs in health care.
+ Knowledge is stored in OpenSearch.
+ For more information, see [Knowledge](/knowledge).
3. To confirm the agent is correct, click **Knowledge**.
- The **Knowledge** page lists the documents OpenRAG has ingested into the OpenSearch vector database. Click on a document to display the chunks derived from splitting the default documents into the vector database.
+ The **Knowledge** page lists the documents OpenRAG has ingested into the OpenSearch vector database.
+ Click on a document to display the chunks derived from splitting the default documents into the vector database.
## Add your own knowledge
1. To add documents to your knowledge base, click **Add Knowledge**.
* Select **Add File** to add a single file from your local machine (mapped with the Docker volume mount).
* Select **Process Folder** to process an entire folder of documents from your local machine (mapped with the Docker volume mount).
+ * Select your cloud storage provider to add knowledge from an OAuth-connected storage provider. For more information, see [OAuth ingestion](/knowledge#oauth-ingestion).
2. Return to the Chat window and ask a question about your loaded data.
For example, with a manual about a PC tablet loaded, ask `How do I connect this device to WiFI?`
The agent responds with a message indicating it now has your knowledge as context for answering questions.
@@ -40,353 +78,289 @@ If you aren't getting the results you need, you can further tune the knowledge i
To modify the knowledge ingestion or Agent behavior, click **Settings**.
In this example, you'll try a different LLM to demonstrate how the Agent's response changes.
+You can only change the **Language model**, and not the **Model provider** that you started with in OpenRAG.
+If you're using Ollama, you can use any installed model.
1. To edit the Agent's behavior, click **Edit in Langflow**.
+You can more quickly access the **Language Model** and **Agent Instructions** fields in this page, but for illustration purposes, navigate to the Langflow visual builder.
2. OpenRAG warns you that you're entering Langflow. Click **Proceed**.
+
3. The OpenRAG OpenSearch Agent flow appears.
+ 
-
-
-4. In the **Language Model** component, under **Model Provider**, select **Anthropic**.
- :::note
- This guide uses an Anthropic model for demonstration purposes. If you want to use a different provider, change the **Model Provider** and **Model Name** fields, and then provide credentials for your selected provider.
- :::
+4. In the **Language Model** component, under **Model**, select a different OpenAI model.
5. Save your flow with Command+S.
6. In OpenRAG, start a new conversation by clicking the in the **Conversations** tab.
7. Ask the same question as before to demonstrate how a different language model changes the results.
## Integrate OpenRAG into your application
-:::tip
-Ensure the `openrag-backend` container has port 8000 exposed in your `docker-compose.yml`:
+To integrate OpenRAG into your application, use the [Langflow API](https://docs.langflow.org/api-reference-api-examples).
+Make requests with Python, TypeScript, or any HTTP client to run one of OpenRAG's default flows and get a response, and then modify the flow further to improve results.
-```yaml
-openrag-backend:
- ports:
- - "8000:8000"
-```
-:::
+Langflow provides code snippets to help you get started with the Langflow API.
-OpenRAG provides a REST API that you can call from Python, TypeScript, or any HTTP client to chat with your documents.
+1. To navigate to the OpenRAG OpenSearch Agent flow, click **Settings**, and then click **Edit in Langflow** in the OpenRAG OpenSearch Agent flow.
+2. Click **Share**, and then click **API access**.
-These example requests are run assuming OpenRAG is in "no-auth" mode.
-For complete API documentation, including authentication, request and response parameters, and example requests, see the API documentation.
+ The default code in the API access pane constructs a request with the Langflow server `url`, `headers`, and a `payload` of request data. The code snippets automatically include the `LANGFLOW_SERVER_ADDRESS` and `FLOW_ID` values for the flow. Replace these values if you're using the code for a different server or flow. The default Langflow server address is http://localhost:7860.
-### Chat with your documents
-
-Prompt OpenRAG at the `/chat` API endpoint.
-
-
-
-
-```python
-import requests
-
-url = "http://localhost:8000/chat"
-payload = {
- "prompt": "What documents are available to you?",
- "previous_response_id": None
-}
-
-response = requests.post(url, json=payload)
-print("OpenRAG Response:", response.json())
-```
-
-
-
-
-```typescript
-import fetch from 'node-fetch';
-
-const response = await fetch("http://localhost:8000/chat", {
- method: "POST",
- headers: { "Content-Type": "application/json" },
- body: JSON.stringify({
- prompt: "What documents are available to you?",
- previous_response_id: null
- })
-});
-
-const data = await response.json();
-console.log("OpenRAG Response:", data);
-```
-
-
-
-
-```bash
-curl -X POST "http://localhost:8000/chat" \
- -H "Content-Type: application/json" \
- -d '{
- "prompt": "What documents are available to you?",
- "previous_response_id": null
- }'
-```
-
-
-
-
-
-Response
-
-```
-{
- "response": "I have access to a wide range of documents depending on the context and the tools enabled in this environment. Specifically, I can search for and retrieve documents related to various topics such as technical papers, articles, manuals, guides, knowledge base entries, and other text-based resources. If you specify a particular subject or type of document you're interested in, I can try to locate relevant materials for you. Let me know what you need!",
- "response_id": "resp_68d3fdbac93081958b8781b97919fe7007f98bd83932fa1a"
-}
-```
-
-
-
-### Search your documents
-
-Search your document knowledge base at the `/search` endpoint.
-
-
-
-
-```python
-import requests
-
-url = "http://localhost:8000/search"
-payload = {"query": "healthcare data quality", "limit": 5}
-
-response = requests.post(url, json=payload)
-results = response.json()
-
-print("Search Results:")
-for result in results.get("results", []):
- print(f"- {result.get('filename')}: {result.get('text', '')[:100]}...")
-```
-
-
-
-
-```typescript
-const response = await fetch("http://localhost:8000/search", {
- method: "POST",
- headers: { "Content-Type": "application/json" },
- body: JSON.stringify({
- query: "healthcare data quality",
- limit: 5
- })
-});
-
-const results = await response.json();
-console.log("Search Results:");
-results.results?.forEach((result, index) => {
- const filename = result.filename || 'Unknown';
- const text = result.text?.substring(0, 100) || '';
- console.log(`${index + 1}. ${filename}: ${text}...`);
-});
-```
-
-
-
-
-```bash
-curl -X POST "http://localhost:8000/search" \
- -H "Content-Type: application/json" \
- -d '{"query": "healthcare data quality", "limit": 5}'
-```
-
-
-
-
-
-
-Example response
-
-```
-Found 5 results
-1. 2506.08231v1.pdf: variables with high performance metrics. These variables might also require fewer replication analys...
-2. 2506.08231v1.pdf: on EHR data and may lack the clinical domain knowledge needed to perform well on the tasks where EHR...
-3. 2506.08231v1.pdf: Abstract Large language models (LLMs) are increasingly used to extract clinical data from electronic...
-4. 2506.08231v1.pdf: these multidimensional assessments, the framework not only quantifies accuracy, but can also be appl...
-5. 2506.08231v1.pdf: observed in only the model metrics, but not the abstractor metrics, it indicates that model errors m...
-```
-
-
-
-### Use chat and search together
-
-Create a complete chat application that combines an interactive terminal chat with session continuity and search functionality.
-
-
-
-
-```python
-import requests
-
-# Configuration
-OPENRAG_BASE_URL = "http://localhost:8000"
-CHAT_URL = f"{OPENRAG_BASE_URL}/chat"
-SEARCH_URL = f"{OPENRAG_BASE_URL}/search"
-DEFAULT_SEARCH_LIMIT = 5
-
-def chat_with_openrag(message, previous_response_id=None):
- try:
- response = requests.post(CHAT_URL, json={
- "prompt": message,
- "previous_response_id": previous_response_id
- })
- response.raise_for_status()
- data = response.json()
- return data.get("response"), data.get("response_id")
- except Exception as e:
- return f"Error: {str(e)}", None
-
-def search_documents(query, limit=DEFAULT_SEARCH_LIMIT):
- try:
- response = requests.post(SEARCH_URL, json={
- "query": query,
- "limit": limit
- })
- response.raise_for_status()
- data = response.json()
- return data.get("results", [])
- except Exception as e:
- return []
-
-# Interactive chat with session continuity and search
-previous_response_id = None
-while True:
- question = input("Your question (or 'search ' to search): ").strip()
- if question.lower() in ['quit', 'exit', 'q']:
- break
- if not question:
- continue
+
+
- if question.lower().startswith('search '):
- query = question[7:].strip()
- print("Searching documents...")
- results = search_documents(query)
- print(f"\nFound {len(results)} results:")
- for i, result in enumerate(results, 1):
- filename = result.get('filename', 'Unknown')
- text = result.get('text', '')[:100]
- print(f"{i}. {filename}: {text}...")
- print()
- else:
- print("OpenRAG is thinking...")
- result, response_id = chat_with_openrag(question, previous_response_id)
- print(f"OpenRAG: {result}\n")
- previous_response_id = response_id
-```
-
-
-
-
-```ts
-import fetch from 'node-fetch';
-
-// Configuration
-const OPENRAG_BASE_URL = "http://localhost:8000";
-const CHAT_URL = `${OPENRAG_BASE_URL}/chat`;
-const SEARCH_URL = `${OPENRAG_BASE_URL}/search`;
-const DEFAULT_SEARCH_LIMIT = 5;
-
-async function chatWithOpenRAG(message: string, previousResponseId?: string | null) {
- try {
- const response = await fetch(CHAT_URL, {
- method: "POST",
- headers: { "Content-Type": "application/json" },
- body: JSON.stringify({
- prompt: message,
- previous_response_id: previousResponseId
- })
- });
- const data = await response.json();
- return [data.response || "No response received", data.response_id || null];
- } catch (error) {
- return [`Error: ${error}`, null];
+ ```python
+ import requests
+ import os
+ import uuid
+
+ api_key = 'LANGFLOW_API_KEY'
+ url = "http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID" # The complete API endpoint URL for this flow
+
+ # Request payload configuration
+ payload = {
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "hello world!"
}
-}
+ payload["session_id"] = str(uuid.uuid4())
+
+ headers = {"x-api-key": api_key}
+
+ try:
+ # Send API request
+ response = requests.request("POST", url, json=payload, headers=headers)
+ response.raise_for_status() # Raise exception for bad status codes
+
+ # Print response
+ print(response.text)
+
+ except requests.exceptions.RequestException as e:
+ print(f"Error making API request: {e}")
+ except ValueError as e:
+ print(f"Error parsing response: {e}")
+ ```
+
+
+
+
+ ```typescript
+ const crypto = require('crypto');
+ const apiKey = 'LANGFLOW_API_KEY';
+ const payload = {
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "hello world!"
+ };
+ payload.session_id = crypto.randomUUID();
+
+ const options = {
+ method: 'POST',
+ headers: {
+ 'Content-Type': 'application/json',
+ "x-api-key": apiKey
+ },
+ body: JSON.stringify(payload)
+ };
+
+ fetch('http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID', options)
+ .then(response => response.json())
+ .then(response => console.warn(response))
+ .catch(err => console.error(err));
+ ```
+
+
+
+
+ ```bash
+ curl --request POST \
+ --url 'http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID?stream=false' \
+ --header 'Content-Type: application/json' \
+ --header "x-api-key: LANGFLOW_API_KEY" \
+ --data '{
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "hello world!",
+ }'
+ ```
+
+
+
-async function searchDocuments(query: string, limit: number = DEFAULT_SEARCH_LIMIT) {
- try {
- const response = await fetch(SEARCH_URL, {
- method: "POST",
- headers: { "Content-Type": "application/json" },
- body: JSON.stringify({ query, limit })
- });
- const data = await response.json();
- return data.results || [];
- } catch (error) {
- return [];
+3. Copy the snippet, paste it in a script file, and then run the script to send the request. If you are using the curl snippet, you can run the command directly in your terminal.
+
+If the request is successful, the response includes many details about the flow run, including the session ID, inputs, outputs, components, durations, and more.
+The following is an example of a response from running the **Simple Agent** template flow:
+
+
+Result
+
+```json
+{
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "outputs": [
+ {
+ "inputs": {
+ "input_value": "hello world!"
+ },
+ "outputs": [
+ {
+ "results": {
+ "message": {
+ "text_key": "text",
+ "data": {
+ "timestamp": "2025-06-16 19:58:23 UTC",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "text": "Hello world! 🌍 How can I assist you today?",
+ "files": [],
+ "error": false,
+ "edit": false,
+ "properties": {
+ "text_color": "",
+ "background_color": "",
+ "edited": false,
+ "source": {
+ "id": "Agent-ZOknz",
+ "display_name": "Agent",
+ "source": "gpt-4o-mini"
+ },
+ "icon": "bot",
+ "allow_markdown": false,
+ "positive_feedback": null,
+ "state": "complete",
+ "targets": []
+ },
+ "category": "message",
+ "content_blocks": [
+ {
+ "title": "Agent Steps",
+ "contents": [
+ {
+ "type": "text",
+ "duration": 2,
+ "header": {
+ "title": "Input",
+ "icon": "MessageSquare"
+ },
+ "text": "**Input**: hello world!"
+ },
+ {
+ "type": "text",
+ "duration": 226,
+ "header": {
+ "title": "Output",
+ "icon": "MessageSquare"
+ },
+ "text": "Hello world! 🌍 How can I assist you today?"
+ }
+ ],
+ "allow_markdown": true,
+ "media_url": null
+ }
+ ],
+ "id": "f3d85d9a-261c-4325-b004-95a1bf5de7ca",
+ "flow_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "duration": null
+ },
+ "default_value": "",
+ "text": "Hello world! 🌍 How can I assist you today?",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "files": [],
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "timestamp": "2025-06-16T19:58:23+00:00",
+ "flow_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "error": false,
+ "edit": false,
+ "properties": {
+ "text_color": "",
+ "background_color": "",
+ "edited": false,
+ "source": {
+ "id": "Agent-ZOknz",
+ "display_name": "Agent",
+ "source": "gpt-4o-mini"
+ },
+ "icon": "bot",
+ "allow_markdown": false,
+ "positive_feedback": null,
+ "state": "complete",
+ "targets": []
+ },
+ "category": "message",
+ "content_blocks": [
+ {
+ "title": "Agent Steps",
+ "contents": [
+ {
+ "type": "text",
+ "duration": 2,
+ "header": {
+ "title": "Input",
+ "icon": "MessageSquare"
+ },
+ "text": "**Input**: hello world!"
+ },
+ {
+ "type": "text",
+ "duration": 226,
+ "header": {
+ "title": "Output",
+ "icon": "MessageSquare"
+ },
+ "text": "Hello world! 🌍 How can I assist you today?"
+ }
+ ],
+ "allow_markdown": true,
+ "media_url": null
+ }
+ ],
+ "duration": null
+ }
+ },
+ "artifacts": {
+ "message": "Hello world! 🌍 How can I assist you today?",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "files": [],
+ "type": "object"
+ },
+ "outputs": {
+ "message": {
+ "message": "Hello world! 🌍 How can I assist you today?",
+ "type": "text"
+ }
+ },
+ "logs": {
+ "message": []
+ },
+ "messages": [
+ {
+ "message": "Hello world! 🌍 How can I assist you today?",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "stream_url": null,
+ "component_id": "ChatOutput-aF5lw",
+ "files": [],
+ "type": "text"
+ }
+ ],
+ "timedelta": null,
+ "duration": null,
+ "component_display_name": "Chat Output",
+ "component_id": "ChatOutput-aF5lw",
+ "used_frozen_result": false
+ }
+ ]
}
+ ]
}
-
-// Interactive chat with session continuity and search
-let previousResponseId = null;
-const readline = require('readline');
-const rl = readline.createInterface({ input: process.stdin, output: process.stdout });
-
-const askQuestion = () => {
- rl.question("Your question (or 'search ' to search): ", async (question) => {
- if (question.toLowerCase() === 'quit' || question.toLowerCase() === 'exit' || question.toLowerCase() === 'q') {
- console.log("Goodbye!");
- rl.close();
- return;
- }
- if (!question.trim()) {
- askQuestion();
- return;
- }
-
- if (question.toLowerCase().startsWith('search ')) {
- const query = question.substring(7).trim();
- console.log("Searching documents...");
- const results = await searchDocuments(query);
- console.log(`\nFound ${results.length} results:`);
- results.forEach((result, i) => {
- const filename = result.filename || 'Unknown';
- const text = result.text?.substring(0, 100) || '';
- console.log(`${i + 1}. ${filename}: ${text}...`);
- });
- console.log();
- } else {
- console.log("OpenRAG is thinking...");
- const [result, responseId] = await chatWithOpenRAG(question, previousResponseId);
- console.log(`\nOpenRAG: ${result}\n`);
- previousResponseId = responseId;
- }
- askQuestion();
- });
-};
-
-console.log("OpenRAG Chat Interface");
-console.log("Ask questions about your documents. Type 'quit' to exit.");
-console.log("Use 'search ' to search documents directly.\n");
-askQuestion();
```
-
-
-
-
-
-Example response
-
-```
-Your question (or 'search ' to search): search healthcare
-Searching documents...
-
-Found 5 results:
-1. 2506.08231v1.pdf: variables with high performance metrics. These variables might also require fewer replication analys...
-2. 2506.08231v1.pdf: on EHR data and may lack the clinical domain knowledge needed to perform well on the tasks where EHR...
-3. 2506.08231v1.pdf: Abstract Large language models (LLMs) are increasingly used to extract clinical data from electronic...
-4. 2506.08231v1.pdf: Acknowledgements Darren Johnson for support in publication planning and management. The authors used...
-5. 2506.08231v1.pdf: Ensuring Reliability of Curated EHR-Derived Data: The Validation of Accuracy for LLM/ML-Extracted In...
-
-Your question (or 'search ' to search): what's the weather today?
-OpenRAG is thinking...
-OpenRAG: I don't have access to real-time weather data. Could you please provide me with your location? Then I can help you find the weather information.
-
-Your question (or 'search ' to search): newark nj
-OpenRAG is thinking...
-```
-
-## Next steps
-TBD
\ No newline at end of file
+To further explore the API, see:
+
+* The Langflow [Quickstart](https://docs.langflow.org/quickstart#extract-data-from-the-response) extends this example with extracting fields from the response.
+* [Get started with the Langflow API](https://docs.langflow.org/api-reference-api-examples)
\ No newline at end of file
diff --git a/src/services/langflow_file_service.py b/src/services/langflow_file_service.py
index 132cd45e..39c5eac7 100644
--- a/src/services/langflow_file_service.py
+++ b/src/services/langflow_file_service.py
@@ -130,9 +130,16 @@ class LangflowFileService:
)
# Avoid logging full payload to prevent leaking sensitive data (e.g., JWT)
+ headers={
+ "X-Langflow-Global-Var-JWT": str(jwt_token),
+ "X-Langflow-Global-Var-OWNER": str(owner),
+ "X-Langflow-Global-Var-OWNER_NAME": str(owner_name),
+ "X-Langflow-Global-Var-OWNER_EMAIL": str(owner_email),
+ "X-Langflow-Global-Var-CONNECTOR_TYPE": str(connector_type),
+ }
resp = await clients.langflow_request(
- "POST", f"/api/v1/run/{self.flow_id_ingest}", json=payload
+ "POST", f"/api/v1/run/{self.flow_id_ingest}", json=payload, headers=headers
)
logger.debug(
"[LF] Run response", status_code=resp.status_code, reason=resp.reason_phrase
@@ -168,7 +175,7 @@ class LangflowFileService:
"""
Combined upload, ingest, and delete operation.
First uploads the file, then runs ingestion on it, then optionally deletes the file.
-
+
Args:
file_tuple: File tuple (filename, content, content_type)
session_id: Optional session ID for the ingestion flow
@@ -176,12 +183,12 @@ class LangflowFileService:
settings: Optional UI settings to convert to component tweaks
jwt_token: Optional JWT token for authentication
delete_after_ingest: Whether to delete the file from Langflow after ingestion (default: True)
-
+
Returns:
Combined result with upload info, ingestion result, and deletion status
"""
logger.debug("[LF] Starting combined upload and ingest operation")
-
+
# Step 1: Upload the file
try:
upload_result = await self.upload_user_file(file_tuple, jwt_token=jwt_token)
@@ -190,10 +197,12 @@ class LangflowFileService:
extra={
"file_id": upload_result.get("id"),
"file_path": upload_result.get("path"),
- }
+ },
)
except Exception as e:
- logger.error("[LF] Upload failed during combined operation", extra={"error": str(e)})
+ logger.error(
+ "[LF] Upload failed during combined operation", extra={"error": str(e)}
+ )
raise Exception(f"Upload failed: {str(e)}")
# Step 2: Prepare for ingestion
@@ -203,9 +212,11 @@ class LangflowFileService:
# Convert UI settings to component tweaks if provided
final_tweaks = tweaks.copy() if tweaks else {}
-
+
if settings:
- logger.debug("[LF] Applying ingestion settings", extra={"settings": settings})
+ logger.debug(
+ "[LF] Applying ingestion settings", extra={"settings": settings}
+ )
# Split Text component tweaks (SplitText-QIKhg)
if (
@@ -216,7 +227,9 @@ class LangflowFileService:
if "SplitText-QIKhg" not in final_tweaks:
final_tweaks["SplitText-QIKhg"] = {}
if settings.get("chunkSize"):
- final_tweaks["SplitText-QIKhg"]["chunk_size"] = settings["chunkSize"]
+ final_tweaks["SplitText-QIKhg"]["chunk_size"] = settings[
+ "chunkSize"
+ ]
if settings.get("chunkOverlap"):
final_tweaks["SplitText-QIKhg"]["chunk_overlap"] = settings[
"chunkOverlap"
@@ -228,9 +241,14 @@ class LangflowFileService:
if settings.get("embeddingModel"):
if "OpenAIEmbeddings-joRJ6" not in final_tweaks:
final_tweaks["OpenAIEmbeddings-joRJ6"] = {}
- final_tweaks["OpenAIEmbeddings-joRJ6"]["model"] = settings["embeddingModel"]
+ final_tweaks["OpenAIEmbeddings-joRJ6"]["model"] = settings[
+ "embeddingModel"
+ ]
- logger.debug("[LF] Final tweaks with settings applied", extra={"tweaks": final_tweaks})
+ logger.debug(
+ "[LF] Final tweaks with settings applied",
+ extra={"tweaks": final_tweaks},
+ )
# Step 3: Run ingestion
try:
@@ -244,10 +262,7 @@ class LangflowFileService:
except Exception as e:
logger.error(
"[LF] Ingestion failed during combined operation",
- extra={
- "error": str(e),
- "file_path": file_path
- }
+ extra={"error": str(e), "file_path": file_path},
)
# Note: We could optionally delete the uploaded file here if ingestion fails
raise Exception(f"Ingestion failed: {str(e)}")
@@ -256,10 +271,13 @@ class LangflowFileService:
file_id = upload_result.get("id")
delete_result = None
delete_error = None
-
+
if delete_after_ingest and file_id:
try:
- logger.debug("[LF] Deleting file after successful ingestion", extra={"file_id": file_id})
+ logger.debug(
+ "[LF] Deleting file after successful ingestion",
+ extra={"file_id": file_id},
+ )
await self.delete_user_file(file_id)
delete_result = {"status": "deleted", "file_id": file_id}
logger.debug("[LF] File deleted successfully")
@@ -267,26 +285,27 @@ class LangflowFileService:
delete_error = str(e)
logger.warning(
"[LF] Failed to delete file after ingestion",
- extra={
- "error": delete_error,
- "file_id": file_id
- }
+ extra={"error": delete_error, "file_id": file_id},
)
- delete_result = {"status": "delete_failed", "file_id": file_id, "error": delete_error}
+ delete_result = {
+ "status": "delete_failed",
+ "file_id": file_id,
+ "error": delete_error,
+ }
# Return combined result
result = {
"status": "success",
"upload": upload_result,
"ingestion": ingest_result,
- "message": f"File '{upload_result.get('name')}' uploaded and ingested successfully"
+ "message": f"File '{upload_result.get('name')}' uploaded and ingested successfully",
}
-
+
if delete_after_ingest:
result["deletion"] = delete_result
if delete_result and delete_result.get("status") == "deleted":
result["message"] += " and cleaned up"
elif delete_error:
result["message"] += f" (cleanup warning: {delete_error})"
-
+
return result