This example uses a local Langflow instance, and it asks the LLM to evaluate a sample resume. If you don't have a resume on hand, you can download fake-resume.txt.
-For help with constructing file upload requests in Python, JavaScript, and curl, see the Langflow File Upload Utility.
For help with constructing file upload requests in Python, JavaScript, and curl, see the Langflow File Upload Utility.
To construct the request, gather the following information:
diff --git a/chat-with-rag.html b/chat-with-rag.html index 2149945714..8efcad4b7d 100644 --- a/chat-with-rag.html +++ b/chat-with-rag.html @@ -24,7 +24,7 @@ - + @@ -90,7 +90,7 @@ Continue the tutorial to learn how to use the loading flow to load data into you The file is loaded to your Langflow server.To load data programmatically, use the /v2/files/ and /v1/run/$FLOW_ID endpoints. The first endpoint loads a file to your Langflow server, and then returns an uploaded file path. The second endpoint runs the Load Data Flow, referencing the uploaded file path, to chunk, embed, and load the data into the vector store.
The following script demonstrates this process. -For help with creating this script, use the Langflow File Upload Utility.
_37// Node 18+ example using global fetch, FormData, and Blob_37import fs from 'fs/promises';_37_37// 1. Prepare the form data with the file to upload_37const fileBuffer = await fs.readFile('FILE_NAME');_37const data = new FormData();_37data.append('file', new Blob([fileBuffer]), 'FILE_NAME');_37const headers = { 'x-api-key': 'LANGFLOW_API_KEY' };_37_37// 2. Upload the file to Langflow_37const uploadRes = await fetch('LANGFLOW_SERVER_ADDRESS/api/v2/files/', {_37 method: 'POST',_37 headers,_37 body: data_37});_37const uploadData = await uploadRes.json();_37const uploadedPath = uploadData.path;_37_37// 3. Call the Langflow run endpoint with the uploaded file path_37const payload = {_37 input_value: "Analyze this file",_37 output_type: "chat",_37 input_type: "text",_37 tweaks: {_37 'FILE_COMPONENT_NAME': {_37 path: uploadedPath_37 }_37 }_37};_37const runRes = await fetch('LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID', {_37 method: 'POST',_37 headers: { 'Content-Type': 'application/json', 'x-api-key': 'LANGFLOW_API_KEY' },_37 body: JSON.stringify(payload)_37});_37const langflowData = await runRes.json();_37// Output only the message_37console.log(langflowData.outputs?.[0]?.outputs?.[0]?.results?.message?.data?.text);
_37// Node 18+ example using global fetch, FormData, and Blob_37import fs from 'fs/promises';_37_37// 1. Prepare the form data with the file to upload_37const fileBuffer = await fs.readFile('FILE_NAME');_37const data = new FormData();_37data.append('file', new Blob([fileBuffer]), 'FILE_NAME');_37const headers = { 'x-api-key': 'LANGFLOW_API_KEY' };_37_37// 2. Upload the file to Langflow_37const uploadRes = await fetch('LANGFLOW_SERVER_ADDRESS/api/v2/files/', {_37 method: 'POST',_37 headers,_37 body: data_37});_37const uploadData = await uploadRes.json();_37const uploadedPath = uploadData.path;_37_37// 3. Call the Langflow run endpoint with the uploaded file path_37const payload = {_37 input_value: "Analyze this file",_37 output_type: "chat",_37 input_type: "text",_37 tweaks: {_37 'FILE_COMPONENT_NAME': {_37 path: uploadedPath_37 }_37 }_37};_37const runRes = await fetch('LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID', {_37 method: 'POST',_37 headers: { 'Content-Type': 'application/json', 'x-api-key': 'LANGFLOW_API_KEY' },_37 body: JSON.stringify(payload)_37});_37const langflowData = await runRes.json();_37// Output only the message_37console.log(langflowData.outputs?.[0]?.outputs?.[0]?.results?.message?.data?.text);
When the flow runs, the flow ingests the selected file, chunks the data, loads the data into the vector store database, and then generates embeddings for the chunks, which are also stored in the vector store.
Your database now contains data with vector embeddings that an LLM can use as context to respond to queries, as demonstrated in the next section of the tutorial.