Skip to main content

Python SDK for the Infratex document intelligence API

Project description

Infratex Python SDK

Official Python client for the Infratex document intelligence API. Parse PDFs, build search indexes, and generate AI-powered answers grounded in your documents.

Installation

pip install infratex

Quick start

from infratex import Infratex

client = Infratex(api_key="infratex_sk_...")

# Upload and parse a PDF
doc = client.documents.upload("report.pdf")
print(doc.id, doc.status, doc.page_count)

# Index for search
index = client.documents.index(doc.id, method="vector")

# Search
results = client.searches.create(query="revenue growth", document_ids=[doc.id])
for r in results:
    print(r.score, r.content[:100])

# AI response (streamed)
for event in client.responses.create(message="Summarize the key findings", document_ids=[doc.id]):
    if event.type == "text":
        print(event.content, end="")
    elif event.type == "sources":
        print("Sources:", event.content)

Authentication

Pass your API key directly or set the INFRATEX_API_KEY environment variable:

# Explicit
client = Infratex(api_key="infratex_sk_...")

# From environment
import os
os.environ["INFRATEX_API_KEY"] = "infratex_sk_..."
client = Infratex()

Resources

Documents

# Upload
# The SDK keeps this ergonomic one-call flow even though the raw HTTP API
# now creates the document first and polls until parsing is complete.
doc = client.documents.upload("report.pdf")
doc = client.documents.upload("report.pdf", method="standard", collection_id="col-id")

# List
docs = client.documents.list(limit=50, offset=0, collection_id="col-id")
print(docs.total)
for d in docs:
    print(d.filename)

# Get
doc = client.documents.get("doc-id")

# Download markdown
md = client.documents.markdown("doc-id")

# Delete
client.documents.delete("doc-id")

# Index
index = client.documents.index("doc-id", method="hybrid")

Searches

results = client.searches.create(
    query="What is the EBITDA?",
    method="vector",
    limit=5,
    document_ids=["doc-id"],
)
for r in results:
    print(r.score, r.content[:200])

Responses (streaming)

for event in client.responses.create(
    message="Summarize the report",
    method="hybrid",
    limit=5,
    document_ids=["doc-id"],
):
    if event.type == "text":
        print(event.content, end="")
    elif event.type == "sources":
        print("Sources:", event.content)
    elif event.type == "done":
        print("\n--- Done ---")
# Managed multi-turn thread with persisted scope
conv = client.conversations.create(
    title="Quarterly Analysis",
    collection_id="col-id",
)

for event in client.responses.create(
    message="How does that compare with the previous quarter?",
    method="hybrid",
    model="pro",
    conversation_id=conv.id,
):
    if event.type == "text":
        print(event.content, end="")

Collections

col = client.collections.create(name="Q3 Reports")
cols = client.collections.list()
col = client.collections.get("col-id")
client.collections.update("col-id", name="Q4 Reports")
client.collections.delete("col-id")

Conversations

conv = client.conversations.create(title="Analysis", collection_id="col-id")
convs = client.conversations.list()
conv = client.conversations.get("conv-id")  # includes messages
client.conversations.delete("conv-id")

Account & Billing

account = client.account.get()
print(account.tenant["email"])

billing = client.billing.get()
print(billing.balance_micros)

Error handling

from infratex import Infratex, InfratexError

client = Infratex(api_key="infratex_sk_...")

try:
    doc = client.documents.get("nonexistent-id")
except InfratexError as e:
    print(e.status_code)  # 404
    print(e.code)         # error code from the API
    print(str(e))         # human-readable message

Configuration

client = Infratex(
    api_key="infratex_sk_...",
    base_url="https://api.infratex.io",  # custom base URL
    timeout=60.0,                         # request timeout in seconds
)

# Use as a context manager
with Infratex(api_key="infratex_sk_...") as client:
    doc = client.documents.upload("report.pdf")

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

infratex-0.4.0.tar.gz (9.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

infratex-0.4.0-py3-none-any.whl (15.2 kB view details)

Uploaded Python 3

File details

Details for the file infratex-0.4.0.tar.gz.

File metadata

  • Download URL: infratex-0.4.0.tar.gz
  • Upload date:
  • Size: 9.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for infratex-0.4.0.tar.gz
Algorithm Hash digest
SHA256 880ede9db6c6e3331c5411ec8501e2e7fb1b142bfab1bdb003075f7c3e569ff8
MD5 9e7306d7b9bb2e48d2c6a642f77191c4
BLAKE2b-256 f6b7fdfae67719f1f2a5dfb687613c01753d04650a8b49b0cec43b0cd9d34e99

See more details on using hashes here.

File details

Details for the file infratex-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: infratex-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 15.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for infratex-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f2eefe81e2a64b3c493bc422a200c173ceb88aa23ea04ff2f5a54559f3d3d24f
MD5 0b59fb5740bbbdcb5751ac4e44564999
BLAKE2b-256 3cf58f994da456382e6b9bcec8cb54c7fdb1c2d7644e326d3595fd8f02af67f6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page